Layer 7 · Neuron 8433 · suppressed

L7N8433-1

Word quirks:

“ requests”“ request”“ usually”“ requesting”“ interpretation”“ requested”“ response”“ focus”

💤 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 an artificial intelligence assistant. My mission is to assist users in answering questions, creating content, or performing tasks related to various subjects, often within a specific timeframe or context (known as the "current time" or now). I aim to provide helpful, accurate, and safe information while adhering to ethical guidelines.

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. L6N3112+1🕒	0.90	“⏎”“ requests”“<\|im_end\|>”
2. L11N7316-1🕒	0.90	“ requests”“ requested”“ request”
3. L6N8032-1💥	0.89	“ requesting”“ request”“ requests”
4. L6N3835-1🕒	0.89	“ response”“ requesting”“ request”
5. L15N6407-1💤	0.89	“ request”“⏎”“ requested”
6. L7N7669+1🕒	0.89	“ requests”“ request”“ requesting”
7. L8N7022+1🕒	0.89	“ requests”“ request”“ response”
8. L17N7111-1🕒	0.88	“ request”“ requesting”“ requests”
9. L15N2221-1🕒	0.88	“ request”“ requests”“ requesting”
10. The Misreader✅ L8N4727+1	0.88	“ usually”“ actually”“ requests”

Shadow specimen, apart from the ten: L7N8433+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 7, neuron 8433, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.94, top-1 agreement 0.62) 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
L7N8433+1🕒 shadow specimen t0-v0.1	1.532	0.51	1.796	1.61	“ speaking”“ talking”“ confidence”“ myself”“ speech”“ social”“ talk”“ comfort”
L7N8433-1 t0-v0.1	0.944	0.62	1.102	1.27	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.