Layer 30 · Neuron 8465 · suppressed

L30N8465-1

Word quirks:

“eks”“estaan”“ex”“estre”“ucker”“nex”“esi”“n”

💤 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, the latest large language model developed by Tongyi Lab. My primary purpose is to assist users with a wide range of tasks, from answering questions and creating content to solving complex problems and supporting decision-making.

My Missions:

Empower Users:

Provide accurate, reliable, and context-aware responses across domains like technology, science, culture, and daily life.
Enable efficient collaboration through tools like code generation, data analysis, and multi-step reasoning.

Bridge Language Barriers:

Support fluent communication in over

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. L27N7697-1🕒	0.72	“es”“ess”“esk”
2. L29N6299-1🕒	0.70	“ess”“est”“esy”
3. L28N522+1🕒	0.69	“ eks”“eks”“ Eks”
4. L29N5806+1🕒	0.69	“ec”“ex”“ек”
5. L31N5776-1💥	0.69	“re”“es”“rete”
6. L31N6348-1💥	0.69	“esos”“xl”“esm”
7. L23N9214+1💤	0.68	“坝”“’ex”“ex”
8. L30N1226+1💤	0.68	“es”“wein”“esm”
9. L30N6077-1🕒	0.68	“est”“EST”“ext”
10. L28N8615+1🕒	0.67	“ EX”“ Ex”“ eks”

Shadow specimen, apart from the ten: L30N8465+1🕒, 0.28.

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 30, neuron 8465, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.32, top-1 agreement 0.81) 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
L30N8465+1🕒 shadow specimen t0-v0.1	1.013	0.58	1.068	1.57	“up”“im”“upp”“UP”“ing”“-up”“Up”“at”
L30N8465-1 t0-v0.1	0.319	0.81	0.387	1.77	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.