arXiv cs.CL· David Nordfors·· 11 小时前AI 评分42
语言模型神经元中的原型语境：一种智能架构？
Archetypal contexts in the neurons of language models: an architecture for intelligence?
AI 导读
研究在 Qwen3.8-27B 内部验证了"原型语境"假说：一组神经元承载跨领域的关系模式（如临界点），另一组承载主题（如政治、生态），第三组承载语言。沉默原型神经元后模型仍识别主题但丢失模式，沉默主题神经元则相反。神经元图谱呈"三明治"分层结构，外层语言、中层主题、核心原型，该结构在预训练中自发形成并出现于所有已测绘模型。
正文 · 原文
Abstract:We validate our previous hypothesis that a language model holds relational patterns apart from the subject domains that instantiate them (Nordfors, 2026). These archetypal contexts are patterns of relations that people recognize across many fields, such as the tipping point or winner takes all, held once and applied across domains. We show this inside the model, Qwen3.8-27B. One set of neurons carries the archetype, say the tipping point; another carries the topic, say politics, ecology or cell biology; a third carries the language, such as English, Spanish or Chinese. Silence the tipping point's neurons, and the model no longer identifies the pattern but still knows what the text is about. Silence the topic's, and it loses the topic but still names the pattern. In the neuron maps the layers organize themselves into a sandwich: the outer layers carry languages, the layers inside them topics, the layers at the heart archetypes. The sandwich emerges spontaneously during pretraining and appears in every model we mapped. Archetypes are the architecture for analogy, and we strongly suggest that this structure of archetypes and topics is the mechanism of a language model's intelligence: we see it self-organize as the model is trained. The neurons, the texts and the code are released with this paper as its reproduction package, so that anyone can repeat the test inside the model.
| Comments: | 18 pages, 7 figures, 2 tables. Reproduction package (neuron sets, texts, answers, code) in the ancillary files |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.07234 [cs.CL] |
| (or arXiv:2611.07234v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07234 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: David Nordfors [view email]
[v1]
Wed, 4 Nov 2026 23:38:46 UTC (39,992 KB)
来源：arXiv cs.CL · arxiv.org