Layer 8 · Neuron 424 · suppressed

L8N424-1

Word quirks:

“ questions”“ question”“ answers”“ answering”“ asking”“ answer”“ your”“ answered”

💤 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 an AI assistant designed to provide helpful information. My mission is to assist users in finding accurate, reliable, and unbiased answers to their questions. I aim to be a supportive resource that can help with a wide range of topics, from academic research and daily life challenges to professional development and personal growth.

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. L17N5804-1🕒	0.98	“ answering”“ answer”“ answers”
2. L14N4564+1💤	0.98	“ answers”“ questions”“ answer”
3. L11N6086+1🕒	0.97	“ questions”“ question”“ answered”
4. L13N2177-1🕒	0.97	“ answer”“ answers”“ question”
5. L8N2271-1🕒	0.97	“ answer”“ question”“ answers”
6. L15N636-1🕒	0.96	“ asking”“ answer”“ answers”
7. L12N2583-1💤	0.95	“ question”“ answer”“ questions”
8. L12N8102-1🕒	0.95	“ question”“ answer”“ questions”
9. L9N5022-1💤	0.95	“ question”“ questions”“ asking”
10. L4N3882-1🕒	0.94	“ question”“ questions”“ reply”

Shadow specimen, apart from the ten: L8N424+1💤, -0.09.

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 8, neuron 424, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.83, 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
L8N424+1💤 shadow specimen t0-v0.1	0.951	0.59	1.148	1.35	“⏎”“ formatting”“ format”“ ⏎”“ simplified”“ `”“ ⏎”“/format”
L8N424-1 t0-v0.1	0.827	0.68	1.007	1.15	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.