Layer 10 · Neuron 6140 · suppressed

L10N6140-1

Word quirks:

“ sometimes”“ ⏎”“ typically”“ ****”“ **”“ ***”“ actually”“ somehow”

💤 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, a large-scale AI model developed by Tongyi Lab. My mission is to assist users in generating high-quality content across various domains, including but not limited to complex reasoning, creative writing, and technical problem-solving. With my advanced capabilities, I can help users complete tasks ranging from simple inquiries to intricate workflows, ensuring efficient and accurate outcomes.

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. L14N7167+1🕒	0.83	“ ⏎”“ *”“ actually”
2. L13N3820-1💤	0.82	“ generally”“ actually”“ **”
3. L11N3360+1🕒	0.81	“ sometimes”“⏎”“ usually”
4. L13N6619-1💤	0.80	“ often”“ typically”“ usually”
5. L11N2252+1💤	0.80	“ somehow”“ sometimes”“ always”
6. L13N8721+1💤	0.80	“ sometimes”“ maybe”“ somehow”
7. L13N8813-1🕒	0.79	“ *”“ generally”“ typically”
8. L12N7556+1💤	0.79	“ sometimes”“ often”“ **"”
9. L10N1336+1💤	0.79	“ special”“ ⏎⏎”“ sometimes”
10. L15N169-1🕒	0.78	“...**”“...\”“ sometimes”

Shadow specimen, apart from the ten: L10N6140+1🕒, 0.47.

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 10, neuron 6140, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.96, top-1 agreement 0.63) 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
L10N6140+1🕒 shadow specimen t0-v0.1	1.401	0.63	1.716	1.52	“ usually”“ __”“<\|im_end\|>”“ typically”“ ____”“ usual”“ indicating”“ ______”
L10N6140-1 t0-v0.1	0.957	0.63	1.181	1.13	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.