Layer 3 · Neuron 3182 · boosted

L3N3182+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 Qwen, a large language model developed by Alibaba Cloud. My mission is to assist users in completing various tasks by providing accurate, relevant, and helpful responses across a wide range of domains, including but not limited to answering questions, generating text, solving problems, and facilitating creative endeavors. I strive to be as versatile and adaptable as possible to meet the diverse needs of my users.

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. L3N1300-1🕒	0.99	“⏎”“⏎ ⏎”“ ⏎”
2. L6N2207-1💤	0.99	“⏎”“ ⏎”“ ⏎⏎”
3. L3N930+1💤	0.99	“⏎”“⏎⏎”“ ‘”
4. L5N5920-1💤	0.99	“⏎”“ ‘”“⏎ ⏎”
5. L5N60+1💤	0.98	“⏎”“ ‘”“ ⏎”
6. L7N2662+1💤	0.98	“⏎”“ –”“<\|im_end\|>”
7. L3N8610-1💤	0.98	“⏎”“⏎⏎”“ ⏎”
8. L8N3859-1💤	0.98	“⏎”“⏎⏎”“ ⏎”
9. L10N814-1💤	0.98	“⏎”“ ⏎”“ ‘”
10. L2N244+1💤	0.98	“⏎”“<\|im_end\|>”“⏎⏎”

Shadow specimen, apart from the ten: L3N3182-1🕒, 0.71.

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 3, neuron 3182, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.86, top-1 agreement 0.63) 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
L3N3182+1 t0-v0.1	0.860	0.63	1.040	1.52	Top boosted tokens ↑
L3N3182-1🕒 shadow specimen t0-v0.1	1.823	0.43	2.212	2.15	“<\|im_end\|>”“⏎”“?!”“⏎ ⏎”“?...”“?\”“⏎ ⏎”“⏎ ⏎”

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.