Layer 10 · Neuron 1791 · boosted

L10N1791+1

Word quirks:

“ ***”“ __”“ usually”“:<”“ sometimes”“ ____”“ "**”“ *"”

💤 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, developed by Tongyi Lab. My mission is to assist users in completing tasks, answering questions, and providing information. However, since I am an AI model, I do not have personal experiences or emotions, but I can help you with various tasks. If you have any specific questions or need assistance with something, feel free to ask me!

But wait, since I am an AI model, I don't have a single identity. Let me think about the most appropriate response for you. Actually, I should say: "I am Qwen3.5, developed by Tongyi Lab

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. L11N7653-1🕒	0.86	“ usually”“ *"”“ sometimes”
2. L11N7258-1💤	0.85	“ **"”“ sometimes”“ often”
3. L13N409+1🕒	0.85	“ sometimes”“ **”“ usual”
4. L13N5408+1💤	0.84	“ ”“ "”“ **"”
5. L12N5126-1🕒	0.83	“ ”“ usually”“ [”
6. L13N5769-1🕒	0.83	“ **”“ often”“ usually”
7. L10N4713+1🕒	0.82	“ usually”“ *”“ **”
8. L11N7031-1💤	0.82	“ normally”“ "”“...”
9. L10N4228+1🕒	0.82	“ usually”“ "”“ ”
10. L14N2477-1💤	0.82	“ ”“ ”“ *"”

Shadow specimen, apart from the ten: L10N1791-1🕒, 0.12.

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 1791, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.98, top-1 agreement 0.62) 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
L10N1791+1 t0-v0.1	0.981	0.62	1.229	1.43	Top boosted tokens ↑
L10N1791-1🕒 shadow specimen t0-v0.1	1.049	0.59	1.250	1.22	“ each”“ ⏎”“ multiple”“ ⏎⏎”“ Each”“ always”“ ⏎”“Each”

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.