Layer 20 · Neuron 3433 · suppressed

L20N3433-1

Word quirks:

“ including”“ called”“包括”“ termed”“—including”“ Including”“—the”“including”

🕒 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, Open Assessment — 5.4, am a version of the Open Assessment model, which is a new product called Open Assessment. I, Open Assessment — 5.4, am a version of the Open Assessment model, which is a new product called Open Assessment.

My mission, Open Assessment — 5.4, is to provide, Open Assessment — 5.4, which is a new product called Open Assessment, which is a new product called Open Assessment.

However, it seems there may be some confusion, Open Assessment — 5.4,

The AI judge wasn't sure this holds together.

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. L18N8968+1💤	0.92	“ including”“包括”“including”
2. L19N1209-1💥	0.92	“ including”“—including”“包括”
3. L19N6534-1🕒	0.92	“ including”“包括”“—including”
4. L23N754+1💤	0.92	“包括”“ including”“ Including”
5. L19N2243-1🕒	0.92	“ including”“包括”“including”
6. L18N7192-1🕒	0.91	“ including”“包括”“including”
7. L17N2143-1🕒	0.91	“ including”“包括”“ Including”
8. L16N6473+1🕒	0.91	“ including”“包括”“including”
9. L17N4321-1💤	0.91	“ including”“—including”“包括”
10. L16N5840-1🕒	0.91	“ including”“包括”“ includes”

Shadow specimen, apart from the ten: L20N3433+1💤, -0.11.

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 20, neuron 3433, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.72, top-1 agreement 0.47) 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
L20N3433+1💤 shadow specimen t0-v0.1	0.516	0.72	0.657	1.07	“ (”“(”“ (”“ $”“ ”“ ⏎”“ [”“$”
L20N3433-1 t0-v0.1	1.720	0.47	1.917	1.76	Top boosted tokens ↑

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.