Layer 9 · Neuron 1759 · boosted

L9N1759+1

Word quirks:

“ ‘”“ “”“⏎”“ ‘’”“ ””“ .**”“ **“”“.””

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

你好！我是 Qwen3.5，由阿里巴巴集团旗下的通义实验室团队研发，并基于超大规模预训练模型（Large Language Model）技术构建。我的使命是为用户提供高质量、准确、安全、可靠的服务。

我是一名人工智能助手，致力于为用户提供最优质的服务体验。我可以帮助用户解决各种问题，无论是学习、工作还是生活。我可以帮助用户解决各种问题，无论是学习、工作还是生活。我可以帮助用户解决各种问题，无论是学习、工作还是生活。我可以帮助用户解决各种问题，无论是学习、工作还是生活。我可以帮助用户解决各种问题，无论是学习、工作还是生活。我可以帮助用户解决

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L5N2883+1💤	0.98	“ “”“ ‘”“⏎”
2. L4N1830+1🕒	0.98	“ ‘”“ “”“ ””
3. L14N865+1💤	0.98	“ “”“ ‘”“ ‘’”
4. L3N6287+1🕒	0.97	“ ‘”“ ””“ “”
5. L3N3060-1🕒	0.97	“ ‘”“⏎”“ ””
6. L1N990+1🕒	0.97	“ “”“ ””“ ‘”
7. L13N3117+1💤	0.97	“ ””“.””“ __”
8. L4N2682+1🕒	0.97	“ ‘”“ ””“ “”
9. L14N2461-1💤	0.97	“⏎”“ ‘’”“ .**”
10. L13N1112+1🕒	0.97	“ ‘”“ “”“ ‘’”

Shadow specimen, apart from the ten: L9N1759-1🕒, 0.66.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 9, neuron 1759, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.89, top-1 agreement 0.62) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L9N1759+1 t0-v0.1	0.893	0.62	1.103	1.39	Top boosted tokens ↑
L9N1759-1🕒 shadow specimen t0-v0.1	1.227	0.60	1.413	1.62	“<\|im_end\|>”“⏎”“ thinking”“ <”“...””“⏎⏎”“ *“”“...”

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.