Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models

Quantum Physics [Submitted on 27 Mar 2026] Entanglement as Memory: Mechanistic Interpretability of Quantum Language Models Nathan Roll Quantum language models have shown competitive performance on sequential tasks, yet whether trained quantum circuits exploit genuinely quantum resources -- or merely embed classical computation in quantum hardware -- remains unknown. Prior work has evaluated these models through endpoint metrics alone, without examining the memory strategies they actually learn internally. We introduce the first mechanistic interpretability study of quantum language models, combining causal gate ablation, entanglement tracking, and density-matrix interchange interventions on a controlled long-range dependency task. We find that single-qubit models are exactly classically simulable and converge to the same geometric strategy as matched classical baselines, while two-qubit models with entangling gates learn a representationally distinct strategy that encodes context in inter-qubit entanglement -- confirmed by three independent causal tests (p < 0.0001, d = 0.89). On real quantum hardware, only the classical geometric strategy survives device noise; the entanglement strategy degrades to chance. These findings open mechanistic interpretability as a tool for the science of quantum language models and reveal a noise-expressivity tradeoff governing which learned strategies survive deployment. Comments: 9 pages, 5 figures, 7 tables Subjects: Quantum Physics (quant-ph); Computation and Language (cs.CL) Cite as: arXiv:2603.26494 [quant-ph]   (or arXiv:2603.26494v1 [quant-ph] for this version)   https://doi.org/10.48550/arXiv.2603.26494 Focus to learn more Submission history From: Nathan Roll [view email] [v1] Fri, 27 Mar 2026 14:57:55 UTC (1,018 KB) Access Paper: HTML (experimental) view license Current browse context: quant-ph < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CL References & Citations INSPIRE HEP NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)