{"total":19,"rows":[{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2410.00593","title":"Style-Specific Neurons for Steering LLMs in Text Style Transfer","created":"2024-10-01","cited_by_count":24,"area":null},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2602.02224","title":"Spectral Superposition: A Theory of Feature Geometry","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2510.04500","title":"Expand Neurons, Not Parameters","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2501.16374","title":"SAFR: Neuron Redistribution for Interpretability","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2506.14775","title":"See What I Mean? CUE: A Cognitive Model of Understanding Explanations","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2410.16484","title":"Identifying Sub-networks in Neural Networks via Functionally Similar Representations","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2510.03320","title":"Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2511.20931","title":"Open Vocabulary Compositional Explanations for Neuron Alignment","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2511.20934","title":"Guaranteed Optimal Compositional Explanations for Neurons","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2605.13340","title":"Shortcut Mitigation via Spurious-Positive Samples","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.20337","title":"Capability $\\neq$ Interpretability: Human Interpretability of Vision Foundation Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.20431","title":"Sparsity, Superposition, and Forgetting: A Mechanistic Study of Representation Retention in Continual Learning","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.13198","title":"SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}