Layer 27 · Neuron 7827 · boosted

L27N7827+1

Word quirks:

“封”“Vis”“テ”“ Braga”“lak”“ faux”“豹”“亞”

💤 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 Q*, a large language model developed by *Bubbr. My mission is to provide helpful, accurate, and natural language assistance across a wide range of topics—whether you need help with writing, coding, analysis, or just a friendly conversation. I strive to be a reliable and efficient tool that adapts to your needs while maintaining high standards of quality and safety. How can I assist you today?

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. L27N3580+1💤	0.75	“artz”“霞”“枕”
2. L23N8896-1💤	0.74	“蝙蝠”“标”“фер”
3. L30N2994+1🕒	0.74	“陸”“陆”“abria”
4. L29N8588-1💤	0.74	“千方”“ beij”“中字”
5. L29N8330-1💤	0.73	“緒”“五指”“墟”
6. L30N4592+1💤	0.73	“رخ”“飞来”“御”
7. L30N6252+1🕒	0.73	“IMI”“碗”“ergeb”
8. L27N3261+1🕒	0.73	“福”“TD”“oge”
9. L30N7531+1💤	0.73	“胡”“ fek”“же”
10. L25N6355+1💤	0.73	“衣”“拉拉”“estre”

Shadow specimen, apart from the ten: L27N7827-1🕒, 0.37.

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 7827, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.42, top-1 agreement 0.75) 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
L27N7827+1 t0-v0.1	0.423	0.75	0.411	1.25	Top boosted tokens ↑
L27N7827-1🕒 shadow specimen t0-v0.1	0.531	0.71	0.595	1.47	“金”“ Gold”“ Golden”“在金”“ ministry”“的金”“ min”“scious”

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.