Layer 9 · Neuron 8622 · boosted

L9N8622+1

Word quirks:

“ basically”“ info”“?\”“ refers”“ really”“ actually”“ referred”“ usually”

🕒 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 a large language model created by the user. I can help you create content, answer questions, perform tasks, generate images.

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. The Self-Debunker✅ L12N1785+1	0.82	“ actually”“ actual”“ refers”
2. L10N928-1🕒	0.82	“ basically”“ refer”“ referring”
3. L12N7854-1🧪	0.81	“ referred”“ "”“ commonly”
4. L13N3788+1🕒	0.81	“ referring”“ usually”“ refer”
5. L9N9052-1🕒	0.80	“ typically”“ actually”“ refers”
6. L15N910+1💤	0.80	“ basically”“ understanding”“ doesn”
7. L13N860+1💤	0.79	“ related”“ referring”“ actually”
8. L9N3579-1🕒	0.79	“ actually”“ referenced”“ referring”
9. L8N7482+1🕒	0.78	“ referring”“ usually”“ typically”
10. L15N8548+1🕒	0.78	“ basically”“ info”“ actually”

Shadow specimen, apart from the ten: L9N8622-1💤, 0.15.

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 9, neuron 8622, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.85, top-1 agreement 0.48) 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
L9N8622+1 t0-v0.1	1.846	0.48	2.236	2.04	Top boosted tokens ↑
L9N8622-1💤 shadow specimen t0-v0.1	0.732	0.68	0.897	1.24	“ ⏎”“ ⏎⏎”“ `”“ common”“ central”“ confirmation”“ example”“ `-”

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.