Layer 27 · Neuron 4157 · boosted

L27N4157+1

Word quirks:

“礼”“ осві”“食物”“纳”“ Food”“住户”“ food”“劳”

💤 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-scale language model developed by Tonggeling (Databel). My core mission is to assist users in solving problems across diverse scenarios by providing accurate, efficient, and high-quality responses. Whether you need help with:

Complex reasoning (math, science, logic)
Creative tasks (writing stories, scripts, marketing content)
Practical applications (coding, data analysis, business planning)
Or even casual conversations

... I aim to deliver solutions that are both human-aligned and actionable. My

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. L28N3417-1💤	0.82	“食品”“食品的”“食的”
2. L30N4210+1💤	0.82	“宗教”“喇”“食物”
3. L29N6570-1💤	0.82	“碼”“-food”“食物”
4. L30N3487-1💤	0.80	“食品”“astro”“消费”
5. L30N7320-1💥	0.80	“食”“食的”“反”
6. L29N6709+1🕒	0.80	“object”“物”“urs”
7. L30N3820-1💤	0.80	“煦”“蔬菜水果”“áž”
8. L22N5672+1💤	0.78	“菜肴”“宴”“饭菜”
9. L23N1068-1🕒	0.77	“空中”“景物”“ animal”
10. L30N1911-1💤	0.77	“房屋”“状态的”“veg”

Shadow specimen, apart from the ten: L27N4157-1🧪, 0.07.

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 4157, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.34, 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
L27N4157+1 t0-v0.1	0.337	0.81	0.319	1.32	Top boosted tokens ↑
L27N4157-1🧪 shadow specimen t0-v0.1	1.057	0.64	1.145	1.50	“参数”“ Parameters”“ parameters”“ parameter”“Parameters”“参数的”“ Parameter”“Parameter”

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.