Layer 29 · Neuron 140 · boosted

L29N140+1

Word quirks:

“alos”“udin”“ouz”“уди”“ardt”“utta”“onnen”“allon”

💤 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 Qwen3.5, a large language model developed by Tongyi Lab. My mission is to empower users with precise, safe, and helpful assistance across a wide range of tasks. Here's how I aim to deliver on this mission:

Core Capabilities & Mission Focus

Intelligent Problem-Solving

From coding and data analysis to scientific research, I help users tackle complex challenges with accuracy and efficiency.

2 Multilingual & Cross-Modal Support

I communicate fluently in over 100 languages and can process text, images

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. L31N6274-1💥	0.74	“otos”“urian”“audi”
2. L31N139-1💥	0.74	“onato”“untung”“erano”
3. L31N1118+1💥	0.74	“utta”“unti”“ovina”
4. L28N4648+1💤	0.73	“ugt”“ Ung”“_pm”
5. L31N8582-1💥	0.73	“tera”“abar”“udos”
6. L30N2989-1💤	0.73	“atsu”“urre”“فش”
7. L31N2718+1💥	0.73	“uret”“agar”“ubu”
8. L31N7003-1💥	0.73	“ansion”“entes”“urato”
9. L31N2803-1💥	0.72	“umere”“اره”“bian”
10. L31N8438+1💥	0.72	“unan”“onat”“onale”

Shadow specimen, apart from the ten: L29N140-1💥, 0.30.

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 140, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.19, top-1 agreement 0.88) 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
L29N140+1 t0-v0.1	0.186	0.88	0.221	1.39	Top boosted tokens ↑
L29N140-1💥 shadow specimen t0-v0.1	31.631	0.00	31.683	0.13	“ unique”“ Unique”“unique”“Unique”“ uniquely”“独特”“独特的”“_unique”

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.