Machine unlearning is becoming essential for building trustworthy and compliant language models. Yet unlearning success varies considerably across individual samples: some are reliably erased, while others persist despite the same procedure. We argue that this disparity is not only a data-side phenomenon, but also reflects model-internal mechanisms that encode and protect memorized information. We study this problem from a mechanistic perspective based on model circuits--structured interaction pathways that govern how predictions are formed. We propose Circuit-guided Unlearning Difficulty (CUD), a {\em pre-unlearning} metric that assigns each sample a continuous difficulty score using circuit-level signals. Extensive experiments demonstrate that CUD reliably separates intrinsically easy and hard samples, and remains stable across unlearning methods. We identify key circuit-level patterns that reveal a mechanistic signature of difficulty: easy-to-unlearn samples are associated with shorter, shallower interactions concentrated in earlier-to-intermediate parts of the original model, whereas hard samples rely on longer and deeper pathways closer to late-stage computation. Compared to existing qualitative studies, CUD takes a first step toward a principled, fine-grained, and interpretable analysis of unlearning difficulty; and motivates the development of unlearning methods grounded in model mechanisms.

翻译：机器遗忘对于构建可信且合规的语言模型正变得至关重要。然而，不同样本间的遗忘成功率差异显著：一些样本能被可靠地擦除，而另一些则在相同流程下持续存在。我们认为，这种差异不仅是数据侧的现象，也反映了模型内部编码和保护记忆信息的机制。我们基于模型电路——即控制预测如何形成的结构化交互路径——从机制视角研究此问题。我们提出了电路引导的遗忘难度，这是一种**遗忘前**度量，它利用电路级信号为每个样本分配一个连续的难度分数。大量实验表明，CUD能可靠地区分本质上容易和困难的样本，并且在不同的遗忘方法中保持稳定。我们识别了关键的电路级模式，揭示了难度的机制特征：易于遗忘的样本与更短、更浅的交互相关，这些交互集中在原始模型的较早至中间部分；而困难样本则依赖于更接近后期计算的更长、更深的路径。与现有的定性研究相比，CUD朝着对遗忘难度进行原则性、细粒度和可解释的分析迈出了第一步，并激励了基于模型机制的遗忘方法的发展。