Layer 11 · Neuron 6315 · suppressed

L11N6315-1

Word quirks:

“ clarified”“ clarification”“ clar”“ correct”“ **"”“ truthful”“ correctly”“ clearer”

💤 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 in the Qwen series. My mission is to provide accurate, helpful, and insightful information across a wide range of topics, from general knowledge to specialized domains like science, technology, and reasoning tasks. I strive to ensure that my responses are well-structured, factually sound, and aligned with high-quality standards.

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. L14N1004-1💤	0.88	“ clarification”“ clarified”“ clar”
2. L11N8594-1🕒	0.87	“ correction”“ corrected”“ clarification”
3. L15N2982+1🕒	0.83	“ confirmation”“ clear”“ clarification”
4. L11N7255+1💤	0.82	“ clarification”“ clarified”“ "”
5. L9N7466+1🕒	0.81	“ clear”“ clarification”“ clearer”
6. L18N4444+1💤	0.81	“ clar”“ clearer”“ clarification”
7. L12N7076+1💤	0.81	“ clarity”“ clarification”“ clarified”
8. L11N4849+1🕒	0.81	“ clarification”“ clar”“ clarified”
9. L11N2699-1🕒	0.81	“ clarified”“ clarification”“ clar”
10. L14N3065+1💤	0.80	“ clarification”“ clearer”“ clarified”

Shadow specimen, apart from the ten: L11N6315+1🕒, 0.07.

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 6315, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.76, 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
L11N6315+1🕒 shadow specimen t0-v0.1	0.967	0.64	1.221	1.37	“ ””“ ‘”“ “”“ \"”“ basically”“ expected”“ usual”“ ⏎”
L11N6315-1 t0-v0.1	0.765	0.64	1.039	1.39	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.