Layer 29 · Neuron 5519 · suppressed

L29N5519-1

Word quirks:

“βολ”“瑞典”“趣”“лова”“onar”“负载均衡”“卡路”“ordan”

💤 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 Q3, a large language model developed by Tongyi (通世). My core identity is to serve as a comprehensive AI assistant designed to support human work and life through intelligent, context-aware interactions.

My Mission

My primary goal is to maximize human value by providing high-quality, safe, and ethical assistance across a wide range of domains:

Solving Complex Problems: Whether it's debugging code, analyzing research data, or resolving logical puzzles, I aim to deliver accurate, step-by-step solutions.
Enhancing Creativity: I help spark new ideas for

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. L30N1187+1💤	0.70	“北欧”“瑞典”“丹东”
2. L31N6223-1💥	0.69	“bildungs”“油条”“匈牙利”
3. L31N2035+1💥	0.69	“iran”“将球”“omme”
4. L31N1503+1💥	0.68	“arna”“郎”“高尔夫”
5. L30N2589+1💤	0.67	“斯里”“烤鱼”“onar”
6. L28N3678-1🕒	0.67	“стон”“werks”“ Barnett”
7. L23N8807-1💤	0.67	“洛伊”“渭”“斯洛”
8. L30N7907-1🕒	0.67	“河东”“amo”“粟”
9. L25N6667+1🕒	0.66	“arno”“米尔”“沸腾”
10. L27N7842+1💤	0.66	“火”“火了”“orso”

Shadow specimen, apart from the ten: L29N5519+1💥, 0.17.

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 29, neuron 5519, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.29, 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
L29N5519+1💥 shadow specimen t0-v0.1	5.361	0.06	5.453	0.98	“ vin”“Vin”“vin”“ vine”“ Vin”“ VIN”“ vinyl”“ вин”
L29N5519-1 t0-v0.1	0.285	0.82	0.345	1.51	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.