Layer 23 · Neuron 2682 · boosted

L23N2682+1

Word quirks:

“ represented”“ exempl”“represented”“ symbol”“ epit”“ embodied”“ demonstrated”“ illustrated”

🕒 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 exemplified by the name "Demonstrated", a symbol of my role as a demonstrated in the field of represented. My mission is to exemplify the best of demonstrated by represented in the field of exemplified.

*Note: This is a playful, self-illustrated response to demonstrate how I can adapt to different contexts. In reality, I am represented by the name Demonstrated, which is a symbol of my role as a demonstrated in the field of represented. My mission

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. L14N8619-1🕒	0.83	“ embody”“ representing”“ embodies”
2. L13N6027+1🕒	0.81	“ representing”“ representative”“ referenced”
3. L19N8819-1🕒	0.79	“ represented”“ depicted”“ shown”
4. L13N5637+1🕒	0.77	“ representing”“ represented”“ representation”
5. L12N6046+1🕒	0.77	“ showcasing”“ indicative”“ exempl”
6. L12N4323-1🕒	0.77	“ representation”“ representing”“ represent”
7. L11N6968-1🕒	0.77	“ represented”“ representation”“ depicted”
8. L8N8775+1🕒	0.77	“ representing”“ represent”“ example”
9. L9N7656-1🕒	0.76	“ representation”“ representations”“ represented”
10. L13N7345+1🕒	0.76	“ depicted”“ represented”“ embodied”

Shadow specimen, apart from the ten: L23N2682-1💤, 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 23, neuron 2682, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.10, top-1 agreement 0.66) 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
L23N2682+1 t0-v0.1	1.095	0.66	1.119	1.60	Top boosted tokens ↑
L23N2682-1💤 shadow specimen t0-v0.1	0.499	0.75	0.613	1.24	“指定”“ mandated”“ permitted”“ allowed”“ prescribed”“规定”“ forced”“arga”

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.