Layer 18 · Neuron 6978 · boosted

L18N6978+1

Word quirks:

“ represented”“ representation”“ info”“ protection”“—"”“ rating”“ reconstruction”“ ratings”

💤 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, the latest large language model developed by Alibaba's Qwen team. My primary goal is to provide users with high-quality assistance in various domains. Here's a summary of my capabilities:

Key Features:

Comprehensive Assistance: I excel in answering questions, creative writing, logical reasoning, and problem-solving across industries.
Multilingual Support: I support over 100 languages, enabling global communication.
Advanced Capabilities:
Code Generation: I can write, debug, and optimize code (e.g., Python, JavaScript).

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. Zero to Hundred✅ L8N3598-1	0.73	“ rating”“ represented”“ imaginary”
2. L17N5286+1🕒	0.70	“ representations”“ representation”“ represented”
3. L17N3936+1🕒	0.68	“ representation”“ representations”“ represented”
4. L8N8171-1🕒	0.67	“ info”“ representing”“ related”
5. L7N1122-1🕒	0.67	“ solution”“ represented”“⏎”
6. L17N3133+1🕒	0.66	“ \"”“ representing”“ info”
7. L7N951-1🕒	0.66	“ representing”“ representation”“ represented”
8. L15N5687-1🕒	0.66	“ representation”“ resolution”“⏎”
9. L31N5381-1💥	0.66	“ representation”“Representation”“ Representation”
10. L7N3312+1🕒	0.66	“<\|im_end\|>”“ representation”“⏎”

Shadow specimen, apart from the ten: L18N6978-1💤, -0.13.

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 18, neuron 6978, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.45, top-1 agreement 0.74) 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
L18N6978+1 t0-v0.1	0.449	0.74	0.526	1.34	Top boosted tokens ↑
L18N6978-1💤 shadow specimen t0-v0.1	0.501	0.74	0.644	1.02	“⏎”““”“ “”“’:”“”:”“””“ calmly”“ one”

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.