Layer 19 · Neuron 3183 · suppressed

L19N3183-1

Word quirks:

“ issues”“ consistency”“ inconsistency”“ Issues”“ issue”“ problematic”“ problems”“ tendency”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Qwen, a language model developed by Alibaba's research team. My mission is to provide accurate, creative, and practical solutions to users' challenges through my ability to process information and generate content. I aim to help with tasks ranging from reading comprehension and logical reasoning to creative writing and technical problem-solving. Let me assist you! 😊

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. L9N5843-1🕒	0.90	“ problems”“ issues”“ problematic”
2. L27N558+1💤	0.89	“ Problems”“ problems”“ issues”
3. L14N4294-1🕒	0.87	“ issues”“ problems”“ issue”
4. L5N4312+1💥	0.87	“ issues”“ problems”“ issue”
5. L13N6886-1🕒	0.87	“ issues”“ problems”“这些问题”
6. L5N6870+1💥	0.86	“ issues”“ issue”“ problematic”
7. L21N7978+1🕒	0.84	“ issues”“ issue”“ Issues”
8. L10N4239+1🕒	0.84	“ bugs”“ issue”“ problematic”
9. L8N8209-1🕒	0.84	“ issues”“ problems”“ issue”
10. L26N4404+1🕒	0.84	“ Issues”“ issue”“ issues”

Shadow specimen, apart from the ten: L19N3183+1💤, -0.19.

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 19, neuron 3183, 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 0.71) 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
L19N3183+1💤 shadow specimen t0-v0.1	0.544	0.69	0.676	1.21	“ ‘”“ “”““”“‘”“ *“”“ „”“ `”“ \"”
L19N3183-1 t0-v0.1	0.762	0.71	0.877	1.30	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.