Mechanistic Interpretability

引用本概念的论文(2)

• 将 RL 诱导的工具使用定位到单个 Crosscoder 特征 Localizing RL-Induced Tool Use to a Single Crosscoder Feature arXiv 2606.26474
• SPARK:大语言模型潜在推理状态的敏感性引导剖析与控制 SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models arXiv 2607.10296

共现相关概念

在引用本概念的论文中,与下列概念同时出现的次数(降序)。