Layer 13 · Neuron 647 · suppressed

L13N647-1

Word quirks:

“ usually”“ here”“ **[”“ seems”“ basically”“ ***”“ ______”“ really”

💤 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 (or Qwen3.5), a large language model developed by Alibaba Cloud. I'm here to assist you with a wide range of tasks, from solving complex problems to providing deep insights. How can I help 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. L11N5655+1🕒	0.80	“ usually”“ now”“ generally”
2. L11N6832+1💤	0.79	“ usually”“ actually”“ generally”
3. L10N3733+1🕒	0.79	“ usually”“ ______”“ basically”
4. L11N6736-1🕒	0.79	“ basically”“ probably”“ actually”
5. L11N4863+1🕒	0.79	“⏎”“ usually”“ here”
6. L13N4587+1🕒	0.78	“ typically”“ ____”“ usually”
7. L14N3792-1💤	0.78	“ really”“ actually”“ etc”
8. L11N2246-1💤	0.78	“ actually”“ really”“ basically”
9. L11N4985-1💤	0.77	“ "**”“ actually”“ usually”
10. L12N3414-1🕒	0.77	“⏎”“<\|im_end\|>”“ overall”

Shadow specimen, apart from the ten: L13N647+1💤, 0.08.

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 13, neuron 647, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.79, top-1 agreement 0.64) 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
L13N647+1💤 shadow specimen t0-v0.1	0.745	0.68	0.993	1.24	“⏎”“ mentioned”“ ⏎”“ example”“ examples”“ focus”“ related”“ reference”
L13N647-1 t0-v0.1	0.786	0.64	0.954	1.49	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.