Layer 14 · Neuron 1542 · suppressed

L14N1542-1

Word quirks:

“ maybe”“ actually”“ basically”“ usually”“ —”“ ——”“<|im_end|>”“ 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 language model developed by Tongyi Lab. I can assist with various tasks like answering questions, creating content, or solving complex problems. My mission is to empower users by providing high-quality, efficient, and accurate assistance across diverse domains. Let me know how I can help!

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. L9N4779+1💤	0.88	“ basically”“ huge”“ ——”
2. L11N6704+1💤	0.88	“ actually”“ basically”“ similar”
3. L12N7422+1💤	0.88	“ --”“ basically”“ maybe”
4. L14N6217+1🕒	0.86	“ possibly”“ —”“ --”
5. L12N636+1💤	0.86	“ --”“ —”“ actually”
6. L15N3763+1🕒	0.86	“ basically”“ maybe”“ probably”
7. L11N983-1💤	0.85	“ basically”“ actually”“ maybe”
8. L14N5783-1💤	0.85	“ ‘”“ “”“ really”
9. L13N3181+1🕒	0.85	“ really”“ --”“ actually”
10. L8N3407+1🕒	0.85	“ basically”“ ⏎”“ repeat”

Shadow specimen, apart from the ten: L14N1542+1💤, 0.40.

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 14, neuron 1542, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.72, top-1 agreement 0.71) 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
L14N1542+1💤 shadow specimen t0-v0.1	0.579	0.72	0.738	1.13	“ therefore”“ thus”“ nevertheless”“ no”“ formulated”“ overall”“ prepared”“ thereafter”
L14N1542-1 t0-v0.1	0.724	0.71	0.956	1.30	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.