Layer 16 · Neuron 3980 · suppressed

L16N3980-1

Word quirks:

“ **“”“ **"”“ "**”“...**”“ ____”“ **„”“ *“”“ ___”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am a large language model trained by Google. My mission is to assist users with any task they need help with. I aim to provide accurate, helpful, and safe responses.

To clarify my identity:

I am a large language model trained by Google.
My mission is to assist users with any task they need help with. I aim to provide accurate, helpful, and safe responses.

To clarify my identity:

I am a large language model trained by Google.
My mission is to assist users with any task they need help with. I aim to provide accurate

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. L9N409+1💤	0.96	“ “”“ "”“ **”
2. L17N478-1💤	0.96	“ ”“ “”“...**”
3. L15N67+1💤	0.95	“ "”“ “”“ "**”
4. L8N6133+1💤	0.95	“ “”“ "”“ **”
5. The Groundhog✅ L15N2693+1	0.95	“ “”“ now”“ "”
6. L16N4845-1🕒	0.94	“ “”“ "”“ “”
7. L10N7969-1🕒	0.94	“ *“”“ “”“ ””
8. L10N9058+1🕒	0.94	“ “”“ "”“ *“”
9. L10N5567-1🕒	0.94	“ “”“ "”“ ___”
10. L14N239+1💤	0.94	“ “”“ "”“ .”

Shadow specimen, apart from the ten: L16N3980+1💤, -0.16.

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 16, neuron 3980, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.68, 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
L16N3980+1💤 shadow specimen t0-v0.1	0.508	0.73	0.610	1.12	“ different”“ similarly”“ similar”“ differently”“ specific”“ Different”“ ⏎”“ ⏎”
L16N3980-1 t0-v0.1	0.680	0.69	0.906	1.30	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.