Layer 26 · Neuron 7880 · boosted

L26N7880+1

Word quirks:

“近”“跟”“面前”“面”“ mặt”“红”“红光”“限”

🕒 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'm Q * (Tachid), a large-scale language model developed by *Tachid Tech. My core mission is to be a high-quality, reliable, and ethical AI assistant that can:

Accurately answer questions across diverse topics (tech, science, culture, etc.)
Create creative content like stories, code, or marketing copy
Solve complex problems with logical reasoning and step-by-step analysis
Protect user privacy and adhere to strict ethical guidelines
Adaptable to different languages

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. L31N6800-1💥	0.86	“列”“面的”“行”
2. L26N8747-1🕒	0.85	“仰”“抱”“相对”
3. L30N5078-1💤	0.85	“面”“面的”“洞”
4. L0N6655-1💥	0.84	“面”“面面”“面的”
5. L27N7622+1💤	0.84	“面的”“面”“面和”
6. L22N294+1💤	0.84	“加”“近”“在”
7. L27N8295+1💤	0.83	“粉”“面”“粉的”
8. L22N649+1💥	0.83	“在”“与”“被”
9. L28N7397+1💤	0.83	“头”“连”“置”
10. L29N8461+1💤	0.83	“投”“口”“名”

Shadow specimen, apart from the ten: L26N7880-1🕒, 0.41.

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 26, neuron 7880, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.75, top-1 agreement 0.73) 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
L26N7880+1 t0-v0.1	0.748	0.73	0.676	1.57	Top boosted tokens ↑
L26N7880-1🕒 shadow specimen t0-v0.1	0.779	0.72	0.834	1.45	“ First”“рам”“ Sacred”“ redirected”“ีม”“取向”“ zaję”“的第一”

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.