Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level analysis and natural language explanations by (i) identifying causally important attention heads via activation patching, (ii) generating explanations using both template-based and LLM-based methods, and (iii) evaluating faithfulness using ERASER-style metrics adapted for circuit-level attribution. We evaluate on the Indirect Object Identification (IOI) task in GPT-2 Small (124M parameters), identifying six attention heads accounting for 61.4% of the logit difference. Our circuit-based explanations achieve 100% sufficiency but only 22% comprehensiveness, revealing distributed backup mechanisms. LLM-generated explanations outperform template baselines by 64% on quality metrics. We find no correlation (r = 0.009) between model confidence and explanation faithfulness, and identify three failure categories explaining when explanations diverge from mechanisms.
Mechanistic Interpretability of Emotion Inference in Large Language Models
Institute for Creative Technologies, University of Southern California (USC)（创意技术研究所，南加州大学）；Information Sciences Institute, University of Southern California (USC)（信息科学研究所，南加州大学）；Department of Computer Science, University of Southern California (USC)（计算机科学系，南加州大学）；Department of Statistics and Data Science, University of California, Los Angeles (UCLA)（统计与数据科学系，加州大学洛杉矶分校）
From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Saarland Informatics Campus（萨尔兰信息学园区）；Centre for European Research in Trusted AI (CERTAIN)（欧洲可信人工智能研究中心（CERTAIN））；Technische Universität Berlin（柏林工业大学）；IBM Research（IBM研究院）；University of Copenhagen（哥本哈根大学）；University of Groningen（格罗宁根大学）
Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
Fordham University（福特汉姆大学）；Algoverse AI Research（Algoverse AI研究）；Rice University（稻子大学）；UC San Diego（圣地亚哥大学）；Santa Clara University（圣克拉拉大学）；LMU Munich（慕尼黑路德维希-马克西米利安大学）
Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
Stratified Precision；Harvard Medical School（哈佛医学院）；Imperial College London（帝国理工学院伦敦分校）；National Health Service（国家健康服务系统）；Ipsen France（Ipsen法国）；University College London（伦敦大学学院）
Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
University of Manchester（曼彻斯特大学）；University of Sheffield（谢菲尔德大学）；Idiap Research Institute（Idiap研究所）；CRUK National Biomarker Centre, University of Manchester（CRUK国家生物标志物中心，曼彻斯特大学）
From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs
School of Information Science, Beijing Language and Culture University（北京语言大学信息科学学院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）
Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；MIIT Key Laboratory of Pattern Analysis and Machine Intelligence（信息产业部模式分析与机器智能重点实验室）；Institute for AI, Tsinghua University, Beijing, China（清华大学人工智能研究院）
Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
Key Laboratory of Ministry of Education for Brain Inspired Intelligent Perception and Cognition, University of Science and Technology of China（教育部脑科学与智能感知认知重点实验室，中国科学技术大学）
National University of Singapore（新加坡国立大学）；SAP Asia Pte Ltd（SAP亚洲私人有限公司）；Nanyang Technological University（南洋理工大学）；Singapore Institute of Technology（新加坡理工大学）
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
AMAP, Alibaba Group（阿里云实验室，阿里巴巴集团）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；Nanyang Technological University（南洋理工大学）
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；University of Oxford（牛津大学）；Technological University Dublin（都柏林技术大学）；Technische Universität Berlin（柏林技术大学）
Technion – Israel Institute of Technology（技术离子-以色列理工学院）
One of the main challenges in mechanistic interpretability is circuit discovery, determining which parts of a model perform a given task. We build on the Mechanistic Interpretability Benchmark (MIB) and propose three key improvements to circuit discovery. First, we use bootstrapping to identify edges with consistent attribution scores. Second, we introduce a simple ratio-based selection strategy to prioritize strong positive-scoring edges, balancing performance and faithfulness. Third, we replace the standard greedy selection with an integer linear programming formulation. Our methods yield mo…
Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs
Texas A&M University（德克萨斯农工大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Maryland（马里兰大学）；University of California, Riverside（加利福尼亚大学河滨分校）；University of Pittsburgh（匹兹堡大学）
Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学跨学科安全、可靠性与信任中心（SnT））；Amsterdam Business School, University of Amsterdam（阿姆斯特丹大学阿姆斯特丹商学院）；Stanford Graduate School of Business, Stanford University（斯坦福大学斯坦福商学院）
Department of Computer & Information Science & Engineering, University of Florida（佛罗里达大学计算机与信息科学与工程系）；School of Computer Science, University of Oklahoma（俄克拉荷马大学计算机科学学院）；Department of Electrical Engineering and Computer Science, United States Military Academy（美国军事学院电子工程与计算机科学系）
The Latin Substrate: How Language Models Represent and Mediate Script Choice
German Research Center for AI（德国人工智能研究中心）；Saarland University（萨尔兰大学）；Indian Institute of Technology, Madras（印度理工学院-马德拉斯）；Nilekani Centre at AI4Bharat（AI4Bharat的Nilekani中心）
