Layer 8 · Neuron 8422 · suppressed

L8N8422-1

Word quirks:

“ requesting”“ requests”“ previously”“ reporting”“ awaiting”“ request”“ confirmation”“ now”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I am an AI assistant designed to provide information, support learning, and assist with various tasks. My mission is to be helpful, accurate, and engaging in my interactions.

Here is how I operate:

Information Retrieval: I search for up-to-date information on a wide range of topics, from science and history to technology and culture, ensuring users have access to reliable knowledge.
Task Assistance: Whether it's solving math problems, writing stories, drafting emails, or explaining complex concepts, I aim to complete these tasks efficiently and accurately.
Educational Support:

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. L9N4372+1💤	0.89	“ request”“ requesting”“ requests”
2. L11N8795+1💤	0.88	“ requests”“ request”“ requesting”
3. L9N8472-1💤	0.88	“ requests”“ request”“ always”
4. L11N3394+1🕒	0.86	“ now”“ requests”“ awaiting”
5. L10N2944-1🕒	0.85	“ requests”“ request”“ requested”
6. L6N8032-1💥	0.84	“ requesting”“ request”“ requests”
7. L12N7272-1💤	0.84	“ already”“ request”“ previously”
8. L9N1931-1🕒	0.84	“ requests”“ request”“ requesting”
9. L7N7927+1💤	0.84	“ requests”“ requesting”“ prompt”
10. L10N3068-1💤	0.83	“ request”“ requesting”“ requests”

Shadow specimen, apart from the ten: L8N8422+1🕒, 0.05.

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 8422, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, top-1 agreement 0.63) 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
L8N8422+1🕒 shadow specimen t0-v0.1	1.190	0.59	1.373	1.24	“ urban”“ city”“ Urban”“ cities”“ commuters”“ metropolitan”“ downtown”“urban”
L8N8422-1 t0-v0.1	0.841	0.63	1.073	1.37	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.