Layer 7 · Neuron 6278 · suppressed

L7N6278-1

Word quirks:

“ ⏎”“<|im_end|>”“ ⏎”“⏎”“ ⏎⏎”“⏎ ⏎”“ ⏎ ⏎”“ ⏎⏎”

💤 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 AI language model developed by Alibaba Cloud. My mission is to assist users in various tasks, such as data analysis, natural language processing, and more. I am designed to be highly efficient and adaptable, capable of handling complex operations with high accuracy and speed. Whether it's for research, development, or operational support, I aim to provide powerful tools and insights to help users achieve their goals.

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. L8N3737-1💤	1.00	“ ⏎”“ ⏎”“<\|im_end\|>”
2. L2N8783-1🕒	1.00	“<\|im_end\|>”“ ⏎”“ ⏎”
3. L6N1113-1💤	1.00	“⏎”“ ⏎”“ ⏎”
4. L3N7537+1🕒	1.00	“⏎”“ ⏎”“ ⏎”
5. L11N2265+1🕒	1.00	“⏎”“ ⏎”“ ⏎”
6. L7N5367+1🕒	1.00	“ ⏎⏎”“ ⏎”“⏎ ⏎”
7. L7N3159-1💤	1.00	“ ⏎”“ ⏎⏎”“ ⏎”
8. L9N1234+1🕒	1.00	“<\|im_end\|>”“⏎”“ ⏎”
9. L10N1388+1🕒	1.00	“<\|im_end\|>”“ ⏎⏎”“ ⏎⏎”
10. L2N1341-1🕒	1.00	“ ⏎”“⏎”“ ⏎”

Shadow specimen, apart from the ten: L7N6278+1🕒, -0.00.

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 7, neuron 6278, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.90, top-1 agreement 0.61) 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
L7N6278+1🕒 shadow specimen t0-v0.1	1.218	0.61	1.490	1.46	“ precisely”“ ⏎⏎”“ crucial”“ regulated”“ carefully”“ regulating”“ referenced”“ particular”
L7N6278-1 t0-v0.1	0.896	0.61	1.100	1.46	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.