Layer 11 · Neuron 967 · boosted

L11N967+1

Word quirks:

“ ALL”“ EVERY”“ always”“ everything”“ ALWAYS”“ completely”“ every”“ ONLY”

💤 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 Tongyi Lab. My mission is to provide high-quality, accurate, and helpful responses to all users, ensuring that every interaction is as reliable and beneficial as possible. Whether it's answering complex questions, generating creative content, or performing logical reasoning, I strive to maintain the highest standards of performance and user satisfaction.

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. L13N6609-1💤	0.95	“ always”“ ALL”“ everywhere”
2. L11N2876-1🕒	0.95	“ every”“ always”“ everywhere”
3. L11N5424+1🕒	0.94	“ always”“ only”“ ONLY”
4. L10N2509+1🕒	0.93	“!**”“ everywhere”“ EVERY”
5. L11N5147+1💤	0.92	“ everything”“ always”“ EVERY”
6. L10N7825-1🕒	0.92	“ ALL”“ ONLY”“ always”
7. L12N4789-1🕒	0.90	“ always”“ ALWAYS”“ all”
8. L12N8796-1🕒	0.90	“ always”“ every”“ ALWAYS”
9. L12N6896+1🕒	0.90	“ every”“ never”“ always”
10. L12N4369-1🕒	0.89	“ always”“ ALWAYS”“ every”

Shadow specimen, apart from the ten: L11N967-1🕒, 0.06.

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 11, neuron 967, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.68, top-1 agreement 0.64) 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
L11N967+1 t0-v0.1	0.678	0.64	0.877	1.45	Top boosted tokens ↑
L11N967-1🕒 shadow specimen t0-v0.1	1.458	0.55	1.735	1.63	“ published”“ book”“ Book”“ Published”“ reviewed”“ publication”“ penned”“ printed”

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.