Layer 16 · Neuron 3402 · suppressed

L16N3402-1

Word quirks:

“ often”“ commonly”“ mostly”“ frequently”“ typically”“ oft”“ sometimes”“ usually”

💤 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, a large language model developed by Tongyi Lab. My primary mission is to assist users in achieving their goals through versatile capabilities tailored to diverse needs. Here's how I serve different contexts:

For individuals: I help with writing, coding, data analysis, and creative tasks (e.g., drafting emails, debugging code, or generating ideas).
For businesses: I optimize workflows via API integration, such as automating customer service or generating reports.
For enterprises: I support complex enterprise use cases like industry-specific analysis or custom model fine-tuning.

My design focuses on

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. L10N4314-1🕒	0.96	“ often”“ typically”“ sometimes”
2. L12N4805+1💤	0.96	“ often”“ usually”“ commonly”
3. L15N5126+1🕒	0.96	“ often”“ usually”“ commonly”
4. L13N8477-1🕒	0.96	“ often”“ typically”“ usually”
5. L15N6920-1💤	0.96	“ often”“ usually”“ generally”
6. L14N2211+1🕒	0.96	“ often”“ sometimes”“ *”
7. L13N5909+1🕒	0.96	“ often”“ sometimes”“ usually”
8. L10N5621+1🕒	0.96	“ often”“ typically”“ usually”
9. L13N2475-1💤	0.96	“ often”“ sometimes”“ Often”
10. L11N7865-1🕒	0.95	“ usually”“ typically”“ often”

Shadow specimen, apart from the ten: L16N3402+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 3402, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.59, 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
L16N3402+1🕒 shadow specimen t0-v0.1	0.795	0.65	0.953	1.55	“ these”“ translated”“ converters”“ translate”“ this”“ translation”“ translators”“ converted”
L16N3402-1 t0-v0.1	0.588	0.73	0.690	1.16	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.