{"total":9,"rows":[{"id":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"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":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2501.16374","title":"SAFR: Neuron Redistribution for Interpretability","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2509.04655","title":"Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2604.23985","title":"Representational Curvature Modulates Behavioral Uncertainty in Large Language Models","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.09438","title":"fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery","created":"2026-05-10","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}