Layer 11 · Neuron 5180 · suppressed

L11N5180-1

Word quirks:

“ ⏎”“ ⏎⏎”“ reflecting”“ ⏎”“ reflected”“ update”“ reflective”“⏎”

💤 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-scale language model developed by Alibaba Cloud. My mission is to provide high-quality, accurate, and helpful information to users while continuously learning and evolving to meet their diverse needs. I strive to assist users in solving complex problems through advanced reasoning and analysis.

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. L13N3588-1💤	0.92	“ ⏎”“ ⏎”“⏎”
2. L9N5064-1💤	0.90	“ ⏎”“ reflection”“ ⏎”
3. L11N772+1🕒	0.88	“⏎”“ reflected”“ ⏎”
4. L12N6141-1💤	0.87	“⏎”“⏎⏎”“ ⏎⏎”
5. L9N4878+1💤	0.86	“ ⏎”“ ⏎⏎”“⏎”
6. L11N6408-1💤	0.85	“ ⏎⏎”“<\|im_end\|>”“ ⏎”
7. L9N418-1🕒	0.84	“ reflections”“ reflecting”“<\|im_end\|>”
8. L11N3335-1💤	0.84	“⏎⏎”“ reflecting”“ reflected”
9. L8N686+1🕒	0.83	“ ⏎”“⏎”“ acknowledgment”
10. L11N3703+1🕒	0.83	“ ⏎”“ —”“ ⏎⏎”

Shadow specimen, apart from the ten: L11N5180+1🕒, 0.04.

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 5180, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.53, top-1 agreement 0.69) 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
L11N5180+1🕒 shadow specimen t0-v0.1	1.536	0.53	1.896	2.00	“ same”“ still”“ already”“ continuation”“ continued”“ just”“?\”“?!”
L11N5180-1 t0-v0.1	0.535	0.69	0.756	1.24	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.