Layer 16 · Neuron 465 · suppressed

L16N465-1

Word quirks:

“ commonly”“ often”“ typical”“ referenced”“ usually”“ usual”“—you”“ similar”

💤 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 language model developed by Tongyi Lab. I am designed to assist users in creating content, coding, or performing other tasks where my capabilities align with human needs. My mission is to provide clear, accurate, and helpful responses across a wide range of topics, ensuring efficiency and precision in interactions. How would you like to use me?

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. L10N8507+1🕒	0.94	“ usually”“ typically”“ generally”
2. L10N3796-1💤	0.93	“ typically”“ usually”“ commonly”
3. L8N2489-1💤	0.92	“ usually”“ typically”“ normally”
4. L11N9034+1💤	0.92	“ typically”“ typical”“ often”
5. L9N3385+1🕒	0.92	“ commonly”“ typically”“ known”
6. L13N1561-1💤	0.92	“ usually”“ usual”“ typical”
7. L13N8672+1🕒	0.92	“ usually”“ typical”“ typically”
8. L12N9172+1🕒	0.92	“ commonly”“ often”“ typically”
9. L15N9154+1🕒	0.92	“ usually”“ typical”“ often”
10. L13N7813-1🕒	0.91	“ usually”“ often”“ typically”

Shadow specimen, apart from the ten: L16N465+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 16, neuron 465, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.61, top-1 agreement 0.68) 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
L16N465+1💤 shadow specimen t0-v0.1	0.514	0.75	0.681	1.15	“ properly”“ ‘”“ ”“ correctly”“ [”“ correct”“ proper”“ ***”
L16N465-1 t0-v0.1	0.606	0.68	0.770	1.36	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.