Layer 12 · Neuron 4569 · suppressed

L12N4569-1

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, the latest large language model in the Qwen series. My mission is to provide high-quality, accurate, and helpful information across a wide range of topics. Whether you need quick facts, detailed analysis, or creative content, I strive to deliver precise and reliable responses.

If you have any questions about my capabilities, I will do my best to answer them clearly and concisely. This aligns with my core mission to assist users effectively.

How can I help 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. L15N2950+1🕒	0.96	“ “”“ ”“ **„”
2. L15N3020-1🕒	0.96	“ “”“ "”“ **”
3. L10N8585+1💤	0.96	“ “”“ "”“ **‘”
4. L19N370-1🕒	0.95	“ “”“ __”“ ‘”
5. L15N5236-1💤	0.95	“ “”“ ”“ **„”
6. L9N1827+1💤	0.95	“ “”“ ‘”“ **„”
7. L10N5567-1🕒	0.95	“ “”“ "”“ ___”
8. L8N3084+1💤	0.94	“ “”“ ”“ **‘”
9. L10N8323-1🕒	0.94	“ __”“ “”“ ‘”
10. L10N894+1💤	0.94	“ '”“ “”“ "**”

Shadow specimen, apart from the ten: L12N4569+1💤, -0.00.

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 4569, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.53, top-1 agreement 0.69) 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
L12N4569+1💤 shadow specimen t0-v0.1	0.578	0.72	0.798	1.27	“ asked”“ sometimes”“⏎”“ talking”“ asking”“ needed”“ yes”“ requests”
L12N4569-1 t0-v0.1	0.532	0.69	0.688	1.12	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.