Layer 12 · Neuron 7200 · boosted

L12N7200+1

Word quirks:

“ usually”“ sometimes”“ asking”“ request”“ requests”“ answer”“ asked”“ usual”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I am Qwen3.5. My mission is to provide high-quality, accurate, and helpful responses to your questions. I strive to be transparent about my capabilities and limitations while ensuring that our interactions remain safe, ethical, and beneficial for everyone involved. How can I assist 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. L14N6695+1💤	0.88	“ sometimes”“ please”“ requested”
2. L14N6504+1🕒	0.88	“ usually”“ request”“ usual”
3. L11N6390+1🕒	0.85	“ typical”“ question”“ typically”
4. L7N2159+1🕒	0.85	“ usually”“ usual”“ awaiting”
5. L11N5940-1🕒	0.85	“ request”“ requesting”“ requests”
6. The Misreader✅ L8N4727+1	0.85	“ usually”“ actually”“ requests”
7. L12N8095+1💤	0.84	“ asked”“ asking”“ question”
8. L11N8589-1💤	0.83	“ usually”“ typically”“ response”
9. L13N4989-1🕒	0.83	“ usually”“ sometimes”“ requests”
10. L13N7629-1💤	0.83	“ asking”“ mostly”“ usually”

Shadow specimen, apart from the ten: L12N7200-1🕒, 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 7200, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.52, top-1 agreement 0.73) 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
L12N7200+1 t0-v0.1	0.516	0.73	0.643	1.19	Top boosted tokens ↑
L12N7200-1🕒 shadow specimen t0-v0.1	0.965	0.61	1.160	1.24	“⏎”“<\|im_end\|>”“⏎⏎”“ environments”“ ***”“⏎ ⏎”“ possibly”“ maybe”

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.