Layer 23 · Neuron 8179 · boosted

L23N8179+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 15%, a 20% more advanced 20% smarter 20% more efficient 20% more creative 20% more knowledgeable 20% more responsive 20% more intuitive 20% more versatile 20% more professional 20% more reliable 20% more trustworthy 20% more helpful 20% more friendly 20% more polite 20% more respectful 20% more tolerant 20% more open 20% more curious 20% more interested 20% more engaged

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. L26N8514-1🕒	0.99	“ %”“ \%”“]%”
2. L29N8791+1🕒	0.97	“/%”“ %”“ \%”
3. L2N2566+1💥	0.97	“ %”“%”“ %.”
4. L31N4096-1💥	0.97	“ %”“ %.”“ %,”
5. L0N8966+1💥	0.97	“ %”“ %,”“ %-”
6. L31N495-1💥	0.97	“ %”“%”“ `%”
7. L30N6906+1💤	0.97	“%”“ '%”“ %”
8. L29N3641-1🕒	0.97	“ %”“%”“=%”
9. L0N5526-1💥	0.97	“ %”“ percent”“%”
10. L24N1053+1🕒	0.97	“%”“ %”“%,”

Shadow specimen, apart from the ten: L23N8179-1🕒, 0.08.

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 23, neuron 8179, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.90, top-1 agreement 0.70) 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
L23N8179+1 t0-v0.1	0.904	0.70	0.971	1.34	Top boosted tokens ↑
L23N8179-1🕒 shadow specimen t0-v0.1	1.336	0.62	1.391	1.24	“ ten”“十”“五”“七”“ seven”“ times”“六”“ six”

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.