Layer 12 · Neuron 8184 · suppressed

L12N8184-1

Word quirks:

“ comparison”“?\”“ confirmation”“<|im_end|>”“?”“ comparisons”“ purpose”“ clearer”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

I am Qwen3.5. I am a large language model developed by Alibaba Cloud. My mission is to provide high-quality, accurate, and reliable information on a wide range of topics. I can help you with various tasks, such as answering questions, creating content, or even just having a conversation. I hope to be your assistant in this regard.

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. L15N2637+1🕒	0.72	“ comparison”“?\”“...\”
2. L6N3132-1💥	0.71	“<\|im_end\|>”“ Comparison”“ comparison”
3. L8N7766+1🕒	0.66	“<\|im_end\|>”“ compared”“ implying”
4. L14N3873+1💤	0.66	“ because”“ comparison”“ queries”
5. L14N8647+1🕒	0.66	“ what”“ comparing”“ comparison”
6. L14N2351-1💤	0.66	“ comparison”“ “”“ similar”
7. L8N5217+1🕒	0.66	“ comparison”“ comparisons”“<\|im_end\|>”
8. L5N3278-1💥	0.66	“<\|im_end\|>”“ compared”“ previous”
9. L13N3454-1🕒	0.65	“ compared”“ comparison”“ comparing”
10. L16N2390+1🕒	0.65	“ comparison”“ comparing”“ compare”

Shadow specimen, apart from the ten: L12N8184+1🕒, 0.14.

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 8184, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L12N8184+1🕒 shadow specimen t0-v0.1	0.850	0.67	1.139	1.32	“ based”“ response”“ already”“ your”“ interaction”“ typically”“ accurately”“ responding”
L12N8184-1 t0-v0.1	1.092	0.60	1.334	1.57	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.