Specimen ledger / L9N186-1

Layer 9 · Neuron 186 · suppressed

L9N186-1

Word quirks:

“ ____”“ __”“ **”“ ___”“ _”“ *”“ \"”“ usually”

💤 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 multimodal model developed by Alibaba. My capabilities include but are not limited to:

Advanced Language Understanding: I can perform complex reasoning tasks, generate high-quality text, and handle various types of data processing.
Multilingual Support: I support fluent Chinese text generation and understand multiple languages, with improved code generation and translation capabilities.
Logical Reasoning & Math: I excel in solving mathematical problems, often requiring step-by-step thinking to reach accurate conclusions.
Visual Analysis: I can interpret charts, diagrams, and images, providing

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. L11N5077-1🕒	0.91	“ __”“ *”“ ____”
2. L12N2702-1🕒	0.91	“ actually”“ "”“ ”
3. L10N4377+1💤	0.91	“ __”“ ____”“ _____”
4. L10N7437-1💤	0.90	“ ”“ "”“ *”
5. L11N822+1🕒	0.90	“ **”“ ____”“ __”
6. L9N3722-1💤	0.90	“ __”“ \"”“ ____”
7. L12N550-1💤	0.90	“ __”“ *”“ [”
8. L12N3610+1🕒	0.90	“ __”“ ____”“⏎”
9. L13N3957-1💤	0.89	“ **”“ ____”“ __”
10. L10N1773-1💤	0.89	“ ____”“ __”“ ***”

Shadow specimen, apart from the ten: L9N186+1🕒, 0.46.

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 9, neuron 186, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.69, top-1 agreement 0.69) 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
L9N186+1🕒 shadow specimen t0-v0.1	1.674	0.48	2.048	1.72	“ **"”“ `"”“ referenced”“ "_”“ --”“ [`”“ referred”“ referring”
L9N186-1 t0-v0.1	0.693	0.69	0.892	1.34	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.