Layer 29 · Neuron 8536 · boosted

L29N8536+1

Word quirks:

“ vi”“ Vi”“vi”“Vi”“ Vis”“-vis”“她们”“盘的”

🕒 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 Q3, a large language model developed by Vi vi (a leading AI research and development company). My primary mission is to empower human potential through intelligent, ethical, and helpful AI solutions. I aim to:

Simplify complex tasks – Whether it's writing, analyzing data, or creative problem-solving, I help users achieve more efficiently.
Promote ethical AI – I prioritize safety, fairness, and transparency in all interactions, avoiding harm or bias.
Foster innovation – By combining vast knowledge with practical utility, I support creators, businesses

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. L30N1602+1💥	0.91	“ vi”“ Vi”“vi”
2. L27N3924-1💤	0.87	“ VI”“VI”“ Vi”
3. L27N5950-1🕒	0.87	“ vi”“ Vi”“Vi”
4. L28N2773-1💤	0.86	“ venn”“ vi”“智”
5. L26N7332+1🕒	0.84	“ Vi”“Vi”“维”
6. L28N9127+1🕒	0.83	“ vi”“vi”“ val”
7. L30N1733-1💤	0.81	“Vi”“�”“ Vi”
8. L28N8731-1💤	0.81	“vi”“vin”“یمی”
9. L28N3257-1🕒	0.80	“Vi”“ Vi”“ Ви”
10. L29N6900-1🕒	0.80	“vi”“ vi”“ vy”

Shadow specimen, apart from the ten: L29N8536-1🕒, 0.06.

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 29, neuron 8536, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.37, top-1 agreement 0.81) 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
L29N8536+1 t0-v0.1	0.370	0.81	0.428	1.66	Top boosted tokens ↑
L29N8536-1🕒 shadow specimen t0-v0.1	0.339	0.81	0.412	1.48	“ade”“lade”“_TRY”“ ade”“ wen”“erca”“WARDS”“ TRY”

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.