Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted ``computational fingerprints'' detectable through spectral analysis. Using graph signal processing on attention induced token graphs, we track changes in algebraic connectivity (Fiedler value, $\Delta\lambda_2$) under voice alternation across 20 languages and three model families, with a prespecified early window (layers 2--5). Our analysis uncovers clear architectural signatures: Phi-3-Mini shows a dramatic English specific early layer disruption ($\overline{\Delta\lambda_2}_{[2,5]}\!\approx\!-0.446$) while effects in 19 other languages are minimal, consistent with public documentation that positions the model primarily for English use. Qwen2.5-7B displays small, distributed shifts that are largest for morphologically rich languages, and LLaMA-3.2-1B exhibits systematic but muted responses. These spectral signatures correlate strongly with behavioral differences (Phi-3: $r=-0.976$) and are modulated by targeted attention head ablations, linking the effect to early attention structure and confirming functional relevance. Taken together, the findings are consistent with the view that training emphasis can leave detectable computational imprints: specialized processing strategies that manifest as measurable connectivity patterns during syntactic transformations. Beyond voice alternation, the framework differentiates reasoning modes, indicating utility as a simple, training free diagnostic for revealing architectural biases and supporting model reliability analysis.

翻译：不同Transformer架构通过不同的连接模式实现相同的语言计算，从而产生可通过谱分析检测到的模型印记“计算指纹”。通过对注意力诱导的标记图进行图信号处理，我们在20种语言和三个模型族中跟踪语音交替下代数连通性（Fiedler值，$\Delta\lambda_2$）的变化，并预设了早期窗口（第2-5层）。我们的分析揭示了清晰的架构特征：Phi-3-Mini在英语中表现出显著的早期层扰动（$\overline{\Delta\lambda_2}_{[2,5]}\!\approx\!-0.446$），而在其他19种语言中影响极小，这与公开文档中该模型主要面向英语使用的定位一致。Qwen2.5-7B显示出微小且分布式的偏移，在形态丰富的语言中偏移最大，而LLaMA-3.2-1B则表现出系统但微弱的响应。这些谱特征与行为差异高度相关（Phi-3：$r=-0.976$），并可通过有针对性的注意力头消融进行调节，从而将效应与早期注意力结构联系起来并确认其功能相关性。综上所述，这些发现与以下观点一致：训练重点会留下可检测的计算印记——表现为句法转换过程中可测量的连接模式的特化处理策略。除语音交替外，该框架还能区分推理模式，表明其作为一种简单、无需训练的诊断工具，可用于揭示架构偏差并支持模型可靠性分析。