Layer 15 · Neuron 7490 · suppressed

L15N7490-1

Word quirks:

“ just”“ this”“ I”“ reflected”“ only”“ fulfill”“ you”“ fulfilled”

🕒 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. How can I assist you?

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. Just An AI✅ L9N6088-1	0.73	“ your”“ my”“ now”
2. L15N7769+1🕒	0.66	“ similar”“ reflected”“ enough”
3. L14N5427-1💤	0.66	“ this”“⏎”“ you”
4. L9N7541+1🕒	0.65	“ yourself”“ your”“ myself”
5. L20N3023+1🕒	0.64	“ completely”“ you”“ I”
6. L12N6414-1💤	0.64	“ my”“ multiple”“ your”
7. L12N4098+1🕒	0.63	“ exactly”“ you”“ even”
8. L13N7320+1🕒	0.63	“ your”“ yourself”“ waiting”
9. L15N6786+1🕒	0.62	“ after”“ now”“ activated”
10. L8N8738+1💤	0.62	“ ONLY”“ your”“ yourself”

Shadow specimen, apart from the ten: L15N7490+1🕒, -0.26.

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 15, neuron 7490, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.82, top-1 agreement 0.65) 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
L15N7490+1🕒 shadow specimen t0-v0.1	1.088	0.59	1.402	1.60	“ “”“ ”“ ______”“ randomly”“,”“ "”“ ________”“ \"”
L15N7490-1 t0-v0.1	0.818	0.65	1.084	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.