{"total":20,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2508.21258","title":"RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching","created":"2025-08-28","cited_by_count":13,"area":"mechinterp"},{"id":"2407.13594","title":"Validating Mechanistic Interpretations: An Axiomatic Approach","created":"2024-07-18","cited_by_count":4,"area":"mechinterp"},{"id":"2410.21815","title":"Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers","created":"2024-10-29","cited_by_count":3,"area":"mechinterp"},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2506.13727","title":"Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs","created":"2025-06-16","cited_by_count":3,"area":"mechinterp"},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2603.13652","title":"Causal Attribution via Activation Patching","created":"2026-03-13","cited_by_count":2,"area":"mechinterp"},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"id":"2503.05522","title":"Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations","created":"2025-03-07","cited_by_count":1,"area":"mechinterp"},{"id":"2509.25247","title":"Protocode: Prototype-Driven Interpretability for Code Generation in LLMs","created":"2025-09-27","cited_by_count":1,"area":"mechinterp"},{"id":"2602.02726","title":"Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery","created":"2026-02-02","cited_by_count":1,"area":"mechinterp"},{"id":"2605.00474","title":"From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models","created":"2026-05-01","cited_by_count":1,"area":"mechinterp"},{"id":"2509.24808","title":"Query Circuits: Explaining How Language Models Answer User Prompts","created":"2025-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2605.06212","title":"Playing the network backward: A Game Theoretic Attribution Framework","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2610.07583","title":"Mechanistic Interpretability of Atmospheric Rivers in GraphCast","created":"2026-10-06","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}