Layer 30 · Neuron 6334 · boosted

L30N6334+1

Word quirks:

“idr”“anal”“ battre”“opy”“hib”“olt”“plemented”“师”

🕒 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 Qwen3.5, the latest large language model developed by Turboprompt (通易师师). My primary mission is to empower users with reliable, efficient, and intelligent tools to solve a wide range of tasks—whether that's answering questions, creating content, analyzing data, or even coding.

Key Capabilities & Focus Areas:

Precision Reasoning: Solves complex math, logic, and scientific problems step-by-step.
Professional Workbench: Supports full-stack code generation, debugging, and even deploying applications directly in the browser.
**Long-

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. L31N3908+1💥	0.61	“olt”“umer”“fru”
2. L29N9131+1🕒	0.60	“inom”“olet”“工”
3. L31N5031+1💥	0.58	“ohl”“istribu”“вок”
4. L23N192-1💤	0.57	“acio”“ide”“zeichnet”
5. L30N7553+1💤	0.57	“op”“olie”“aten”
6. L31N7945-1💥	0.57	“imes”“olit”“ol”
7. L30N2607+1💤	0.57	“odr”“敏”“obl”
8. L31N8094-1💥	0.56	“enn”“olib”“árn”
9. L27N8486-1💤	0.56	“idor”“idt”“-ons”
10. L30N3391-1💤	0.56	“izzo”“渉”“aup”

Shadow specimen, apart from the ten: L30N6334-1💤, 0.24.

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 30, neuron 6334, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.42, top-1 agreement 0.79) 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
L30N6334+1 t0-v0.1	0.417	0.79	0.488	2.07	Top boosted tokens ↑
L30N6334-1💤 shadow specimen t0-v0.1	0.318	0.84	0.367	1.52	“困难”“unky”“根的”“اده”“اد”“阶”“ٰ”“浩”

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.