Layer 8 · Neuron 5754 · suppressed

L8N5754-1

Word quirks:

“ ‘”“ ____”“ ______”“‘”“ ________”“ _____”“ __”“ ⏎”

💤 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 AI assistant developed by Google. My mission is to provide helpful, accurate, and safe information to users. I do not have personal beliefs or desires, but I strive to be honest and transparent in my responses. I am designed to assist users in solving problems, making decisions, and learning new skills.

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. L14N2592-1💤	0.98	“ “”“ ‘”“ ____”
2. L15N1985+1🕒	0.98	“ ⏎”“ ____”“ ______”
3. L6N8257+1🕒	0.98	“ ‘”“ ____”“ __”
4. L8N4177+1💤	0.98	“ __”“ ______”“ ‘”
5. L6N568-1🕒	0.98	“ ____”“ “”“ ‘”
6. L9N1598-1🕒	0.98	“ ⏎”“ ______”“ ____”
7. L16N6105-1🕒	0.98	“ ____”“ ‘”“ ______”
8. L10N1498+1🕒	0.98	“ ____”“ __”“ ______”
9. L4N262-1💤	0.98	“ ‘”“ ____”“ ______”
10. L4N5968+1💤	0.98	“⏎”“ ‘”“ ____”

Shadow specimen, apart from the ten: L8N5754+1💥, 0.23.

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 5754, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.59, 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
L8N5754+1💥 shadow specimen t0-v0.1	2.810	0.32	3.168	3.53	“<\|im_end\|>”“ organisation”“ systems”“ ””“ organisations”“ ：”“⏎⏎”“\n”
L8N5754-1 t0-v0.1	0.595	0.74	0.739	1.33	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.