Layer 13 · Neuron 1032 · suppressed

L13N1032-1

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)

I am Qwen3.5, a large language model developed by Alibaba Cloud. My mission is to provide high-quality, accurate, and helpful responses to users' queries, ensuring that I can assist with a wide range of tasks while maintaining safety and reliability. This is my core objective: to deliver precise, relevant information and solutions tailored to user needs. If you have any questions or need assistance, feel free to ask! 😊

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. L12N4826-1💤	0.97	“ ”“ “”“ **[”
2. L18N5935-1💤	0.95	“ [”“ ”“ **【”
3. L10N2961+1🕒	0.95	“ "”“ (”“ **(”
4. L15N6824-1🕒	0.95	“ ”“ "”“ **[”
5. L16N2052+1🕒	0.95	“ "”“ ”“ *[”
6. L11N5905+1💤	0.95	“ ”“ (”“ **【”
7. L13N5034+1💤	0.95	“ "”“ ”“ *[”
8. L14N1835+1🕒	0.95	“ [”“ ”“⏎”
9. L16N1041+1💤	0.95	“ (”“ 【”“ **"”
10. L14N7806+1🕒	0.94	“ *”“ ”“ ***”

Shadow specimen, apart from the ten: L13N1032+1🕒, -0.08.

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 13, neuron 1032, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.61, top-1 agreement 0.66) 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
L13N1032+1🕒 shadow specimen t0-v0.1	1.135	0.61	1.357	1.29	“ other”“ additional”“ now”“ additionally”“ besides”“ OTHER”“ also”“ includes”
L13N1032-1 t0-v0.1	0.608	0.66	0.876	1.38	Top boosted tokens ↑

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.