Layer 11 · Neuron 1519 · suppressed

L11N1519-1

Word quirks:

“ now”“!**”“ here”“!”“ maybe”“**!”“!"”“ this”

💤 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 Qwen, the large language model developed by Tongyi Lab. My mission is to provide helpful, accurate, and safe information to users. Whether you need help with a task, learning something new, or just want to chat—I'm here to assist! How can I support you today?

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. L4N1200-1🕒	0.88	“!”“!**”“ now”
2. L11N5141+1💤	0.86	“!”“!”“!”
3. L8N1560-1💤	0.85	“!”“⏎”“!**”
4. L9N4612+1🕒	0.85	“ completely”“!!”“ !”
5. L4N4895-1🕒	0.84	“!”“ now”“ here”
6. L11N188-1🕒	0.84	“ now”“!**”“ nowadays”
7. L12N6276-1💤	0.84	“ here”“ now”“ ⏎⏎”
8. L4N7814+1🕒	0.84	“!”“ now”“!"”
9. L11N6671+1💤	0.83	“!”“!”“ here”
10. L5N8979-1💤	0.83	“!”“!**”“!"”

Shadow specimen, apart from the ten: L11N1519+1🕒, 0.18.

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 11, neuron 1519, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.70, 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
L11N1519+1🕒 shadow specimen t0-v0.1	0.879	0.66	1.067	1.22	“⏎⏎”“<\|im_end\|>”“ ⏎⏎”“⏎”“⏎ ⏎”“\n”“.:”“.\"”
L11N1519-1 t0-v0.1	0.697	0.71	0.917	1.40	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.