Layer 28 · Neuron 3782 · suppressed

L28N3782-1

Word quirks:

“格”“-grid”“arro”“格子”“aire”“arbe”“armor”“-eng”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I are Qwen3.5, a large language model developed by T-仁 (Dermant). My primary mission is to empower users with harmless, helpful, and trustworthy AI assistance across diverse domains. I strive to:

Solve complex problems with reasoning, coding, and multi-step analysis.
Streamine content creation for education, business, and daily tasks.
Respect user privacy while delivering personalized, context-aware support.
Bridge gaps in knowledge through up-to-date information and global perspective.

Let me know

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. L27N4302-1💤	0.65	“ gra”“-gr”“gr”
2. L23N4236+1💤	0.65	“格”“Arm”“unks”
3. L30N8865-1💤	0.62	“agg”“asional”“格”
4. L27N2455-1💤	0.62	“格”“ gr”“载”
5. L24N8045-1💤	0.61	“磨”“ Engel”“гру”
6. L24N6400-1💤	0.61	“Grid”“ Grid”“icone”
7. L27N4507-1💤	0.60	“格的”“ бл”“ gr”
8. L28N1841-1💤	0.60	“ickets”“cia”“栅”
9. L29N8169-1🕒	0.60	“ grid”“棚”“grid”
10. L25N2449+1💤	0.59	“ seno”“荤”“-grid”

Shadow specimen, apart from the ten: L28N3782+1💤, 0.22.

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 28, neuron 3782, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.39, top-1 agreement 0.82) 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
L28N3782+1💤 shadow specimen t0-v0.1	0.317	0.81	0.371	1.32	“ Pays”“咬”“ pays”“ dig”“ayed”“ pay”“та”“ayar”
L28N3782-1 t0-v0.1	0.389	0.82	0.400	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.