Layer 8 · Neuron 8294 · suppressed

L8N8294-1

Word quirks:

“ description”“ basically”“ navigation”“ generated”“ usually”“ containing”“ *”“ function”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

Hello! I am Qwen3.5, a large language model developed by Alibaba Cloud. My primary function is to assist users with information retrieval, complex reasoning tasks, and content generation.

My Mission:
As an AI assistant, my role is to empower users by providing accurate information and facilitating complex workflows. Whether it's answering questions about science, history, or performing calculations, I aim to make life easier for everyone.

Key Capabilities:

Natural Language Understanding: I can understand and generate text in various languages.
Multimodal Processing: I support both text and image inputs (though image

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. L7N2026+1💤	0.65	“ info”“ generated”“ generating”
2. L6N5270-1💤	0.65	“ usually”“ generating”“ generated”
3. L11N5499-1🕒	0.65	“⏎”“ usually”“ generating”
4. L7N7129-1🕒	0.64	“ description”“ generating”“ generated”
5. L9N6682+1💤	0.63	“ generated”“ specific”“ generic”
6. L8N808-1🕒	0.63	“ generating”“ ‘”“ basically”
7. L9N7320+1🕒	0.63	“ usually”“ description”“ usual”
8. L10N1443+1🕒	0.63	“ usually”“ **"”“ typically”
9. L8N5816-1💤	0.63	“ generation”“ generated”“ generating”
10. L6N2868-1💤	0.62	“ usually”“ often”“ generally”

Shadow specimen, apart from the ten: L8N8294+1💤, 0.28.

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 8, neuron 8294, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L8N8294+1💤 shadow specimen t0-v0.1	0.909	0.59	1.186	1.40	“ —”“ always”“ referenced”“ example”“ --”“ description”“ examples”“ ALWAYS”
L8N8294-1 t0-v0.1	1.034	0.61	1.192	1.32	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.