Layer 12 · Neuron 5157 · suppressed

L12N5157-1

Word quirks:

“ nice”“ nicely”“ actually”“ really”“ anyway”“ hypothetical”“ good”“ basically”

💤 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, the latest large language model developed by Tongyi Lab. My mission is to provide high-quality, accurate, and helpful information across a wide range of topics and tasks. Whether you need help with creative writing, logical reasoning, coding, or data analysis, I'm here to assist! How can I support you today? 😊

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. L13N4941+1🕒	0.91	“ really”“ actually”“ basically”
2. L11N4644-1💤	0.91	“ basically”“ good”“ really”
3. L12N8333+1🕒	0.90	“ maybe”“ nicely”“ indeed”
4. L11N7252-1🕒	0.89	“ actually”“ really”“ basically”
5. L10N123+1🕒	0.88	“ maybe”“ stuff”“ basically”
6. L13N3184+1🕒	0.88	“ nice”“ really”“ nicely”
7. L12N7491+1🕒	0.88	“ really”“ nice”“ nicely”
8. L11N2797-1🕒	0.88	“ basically”“ nicely”“ mainly”
9. L9N7299+1🕒	0.88	“ nicely”“ good”“ actually”
10. L16N5599+1🕒	0.88	“ basically”“ really”“ maybe”

Shadow specimen, apart from the ten: L12N5157+1🕒, 0.22.

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 12, neuron 5157, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.69, top-1 agreement 0.68) 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
L12N5157+1🕒 shadow specimen t0-v0.1	0.901	0.61	1.209	1.32	“ only”“ ONLY”“ Only”“ reserved”“ reason”“only”“ sparing”“ because”
L12N5157-1 t0-v0.1	0.690	0.68	0.967	1.10	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.