摘要：大语言模型往往表现出过度自信：当证据表明应当使用审慎措辞或拒绝作答时，它们仍会给出断言式回答。我们使用能够操纵逻辑必然性和可能性的受控推理场景，研究了 Qwen3-4B 在三种不确定性表达方式中的这一行为：语言认识论标记、拒答以及数值置信度评分。结果证实了这种过度自信倾向，尤其是在提示模型输出数值置信度评分时。在可解释性层面，我们提出了一种方法，可差异化识别负责不确定性和确定性的 transcoder 特征。分析显示，Qwen3-4B 的默认机制通过广泛的共享特征联盟偏向于生成确定性，而不确定性则被实现为一种稀疏的覆盖机制，由少量专用特征介导。对这些不确定性特征进行干预，既因果性地证明了导致过度自信的这种失衡，也能够缓解过度自信错误。同一组特征可泛化至三种不确定性表达设定、不同语言以及一项分布外模态任务。

Abstract:Large language models tend to overconfidence, giving assertive answers when the evidence suggests hedging or abstention. Using controlled reasoning scenarios that manipulate logical necessity and possibility, we study this behavior in Qwen3-4B, across three ways to express uncertainty: verbal epistemic markers, abstention, and numeric confidence scores. Our results confirm this tendency toward overconfidence, particularly when the model is prompted to output a numeric confidence score. At the interpretability level, we propose a method that differentially identifies transcoder features responsible for uncertainty and certainty. Our analysis reveals Qwen3-4B's default mechanism favors certainty generation through a broad coalition of shared features, while uncertainty is implemented as a sparse override mediated by a small set of dedicated features. Intervening on these uncertainty features both causally proves this imbalance underlying overconfidence and also mitigate overconfident errors. The same set of features generalise across the three uncertainty-expression settings, languages, and an out-of-distribution modality task.