Layer 27 · Neuron 3920 · boosted

L27N3920+1

Word quirks:

“IX”“loor”“INGER”“rap”“堡”“inx”“ehr”“ IX”

💤 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 Q* (通义千问), a large language model developed by *T (通义实验室). My primary mission is to help humans solve problems, create content, and learn new skills through intelligent interaction.

Key aspects of my role:

Answering questions: From scientific facts to everyday "why" and "how" questions.
Creative support: Writing stories, coding, composing poems, or brainstorming ideas.
Analysis & reasoning: Breaking down complex topics in fields like science, health, or technology.
Language & communication: Translating between

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. L31N8707+1💥	0.67	“ivit”“ix”“IX”
2. L31N2225+1💥	0.66	“IX”“XD”“XE”
3. L31N8077-1💥	0.65	“ixa”“ixo”“ix”
4. L31N9144-1💥	0.65	“u”“ix”“ixed”
5. L22N805+1💤	0.65	“IX”“flow”“extract”
6. L1N74+1💥	0.64	“ix”“ott”“iculo”
7. L30N5787-1💤	0.63	“�”“IX”“lios”
8. L31N7593-1💥	0.62	“ saz”“hic”“ix”
9. L22N2297-1💤	0.62	“ubar”“ XI”“ Friend”
10. L22N3572+1💤	0.62	“IX”“ulum”“aison”

Shadow specimen, apart from the ten: L27N3920-1🕒, 0.05.

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 27, neuron 3920, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.35, top-1 agreement 0.79) 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
L27N3920+1 t0-v0.1	0.354	0.79	0.423	1.27	Top boosted tokens ↑
L27N3920-1🕒 shadow specimen t0-v0.1	1.783	0.50	1.854	1.12	“驱”“ drive”“驱动”“ drove”“ drives”“ Drive”“_drive”“drive”

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.