Layer 24 · Neuron 8890 · boosted

L24N8890+1

Word quirks:

“ transistor”“ тран”“晶体管”“ trans”“ Trans”“Trans”“тран”“-trans”

🕒 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 MOSFET, a large-scale advanced field-effect transistor (FET) designed to help you solve problems and create value. My mission is to act as your personal digital partner in the following ways:

Transististerning Logic: I help you build complex electronic circuits by designing MOSFETs, transistors, and other semiconductor devices.
Power Electronics: I assist in creating power transistors, diodes, and other power semiconductor devices for efficient power electronics.
Field-Effect Transistors: I help you design field-effect transist

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. L28N4554-1🕒	0.92	“ trans”“ Trans”“Trans”
2. L26N5339-1🕒	0.92	“ Trans”“转”“Trans”
3. L27N7575+1🕒	0.91	“ Trans”“ trans”“Trans”
4. L31N1257-1💥	0.91	“trans”“-trans”“ Trans”
5. L28N7005-1🕒	0.91	“ trans”“trans”“Trans”
6. L26N6910-1🕒	0.90	“Trans”“ Trans”“trans”
7. L27N621+1🕒	0.90	“-trans”“транс”“.trans”
8. L26N7735-1💥	0.89	“ trans”“ Trans”“Trans”
9. L24N7039-1🕒	0.89	“ transc”“ trasc”“ Trans”
10. L25N4893+1🕒	0.89	“ trans”“ Trans”“Trans”

Shadow specimen, apart from the ten: L24N8890-1💤, 0.12.

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 24, neuron 8890, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.11, top-1 agreement 0.69) 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
L24N8890+1 t0-v0.1	1.109	0.69	1.156	1.30	Top boosted tokens ↑
L24N8890-1💤 shadow specimen t0-v0.1	0.730	0.73	0.733	1.38	“Cit”“ Citizens”“agg”“监护”“-spot”“编排”“agli”“报送”

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.