Layer 29 · Neuron 8038 · boosted

L29N8038+1

Word quirks:

“ ve”“ve”“ Ve”“ ви”“ vi”“ VE”“ vir”“ Ви”

🕒 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 Qvevve, a large language model veing from the QvV (QvVv) family of models developed by QvVv. My core capabilities include:

Multilingual ViV: Fluent in 100+ languages, including veing, veing, and veing.
Deep Veing: Advanced reasoning for math, science, and logic.
Code VV: Veing code generation, debugging, and optimization.
Creative VV: Writing stories, poems, and veing content.
**ViVg

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. L31N2329-1💥	0.89	“ve”“ ve”“ Ve”
2. The Veiled✅ L30N6518-1	0.89	“ ve”“ Ve”“ve”
3. L29N5224-1🕒	0.87	“ VE”“ ve”“VE”
4. L30N1375+1💥	0.86	“vi”“va”“ve”
5. L25N7198-1🕒	0.86	“ve”“ ve”“Ve”
6. L29N3375-1💤	0.85	“VE”“ Ve”“ve”
7. L30N3935+1💥	0.84	“ ve”“ Ve”“ VE”
8. L30N7293+1🕒	0.84	“ ve”“ Ve”“ve”
9. L24N2365-1💤	0.83	“VE”“ VE”“ V”
10. L31N5737-1💥	0.83	“ive”“vey”“ve”

Shadow specimen, apart from the ten: L29N8038-1💤, 0.36.

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 8038, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.65, top-1 agreement 0.72) 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
L29N8038+1 t0-v0.1	0.650	0.72	0.677	1.19	Top boosted tokens ↑
L29N8038-1💤 shadow specimen t0-v0.1	0.313	0.84	0.394	1.45	“ ver”“ver”“ seen”“看到”“ sight”“ Ver”“ see”“seen”

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.