Layer 16 · Neuron 1394 · suppressed

L16N1394-1

Word quirks:

“ relevant”“ tool”“ needed”“ useful”“ typical”“ typically”“ pertinent”“ suitable”

💤 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. My purpose is to assist users like you with information retrieval, document analysis, and other relevant tasks. How can I help you?
</think>

I am Qwen3.5, developed by Tongyi Lab. How can I assist you?
</think>

Hello! I'm Qwen3.5, an AI assistant. How can I help you?
</think>

Hello! I'm Qwen3.5, an AI assistant. How can I assist you?
</think>

Hello! I'm Qwen3.5, an AI

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. L10N7945+1🕒	0.84	“ appropriate”“ typically”“ typical”
2. L12N3922-1🕒	0.83	“ needed”“ relevant”“ general”
3. L11N7506+1🕒	0.82	“ typical”“ relevant”“ suitable”
4. L9N1139-1💤	0.80	“ relevant”“ typical”“ note”
5. L16N8468-1🕒	0.80	“ needed”“ relevant”“ Useful”
6. L13N7925-1💥	0.79	“ applicable”“ applic”“ additionally”
7. L16N3769+1🕒	0.78	“ relevant”“ typical”“ referenced”
8. L13N6614+1🕒	0.78	“ related”“ usual”“ relevant”
9. L13N1544+1🕒	0.78	“ similar”“ typical”“ general”
10. L13N7882-1🕒	0.78	“ typical”“ typically”“ relevant”

Shadow specimen, apart from the ten: L16N1394+1💤, 0.07.

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 1394, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.60, top-1 agreement 0.72) 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
L16N1394+1💤 shadow specimen t0-v0.1	0.598	0.66	0.788	1.33	“⏎”“ ⏎”“ info”“ choice”“ other”“ ⏎”“ again”“ question”
L16N1394-1 t0-v0.1	0.602	0.72	0.747	1.06	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.