Layer 13 · Neuron 409 · boosted

L13N409+1

Word quirks:

“ sometimes”“ **”“ usual”“ same”“ ____”“ **"”“ __”“ ***”

🕒 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 Tongyi Lab. I am an AI assistant with advanced capabilities in natural language processing, logical reasoning, visual analysis, and code generation. My training involves a vast amount of text data, which helps me understand and generate human-like responses.

What I Can Do:

Answer Questions: Provide accurate information based on my training data.
Solve Problems: Handle tasks like math calculations, logical reasoning, and creative writing.
Generate Content: Create stories, articles, emails, or code as needed.
**Analyze

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. L10N1791+1💤	0.85	“ ***”“ __”“ usually”
2. Yes, Yes, Yes✅ L13N2600-1	0.84	“ sometimes”“ *”“ ”
3. L12N5750+1💤	0.84	“ ”“ ”“ ***”
4. L13N5769-1🕒	0.83	“ **”“ often”“ usually”
5. L10N4713+1🕒	0.83	“ usually”“ *”“ **”
6. L10N1430-1💤	0.82	“ ”“ *"”“ usually”
7. L9N2146+1🕒	0.82	“ ~”“ ***”“ release”
8. L10N676+1💤	0.82	“ sometimes”“ *”“ '”
9. L13N5408+1💤	0.82	“ ”“ "”“ **"”
10. L12N4635-1💤	0.81	“ '”“ ”“ *"”

Shadow specimen, apart from the ten: L13N409-1🕒, 0.18.

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 13, neuron 409, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.86, top-1 agreement 0.64) 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
L13N409+1 t0-v0.1	0.860	0.64	1.072	1.31	Top boosted tokens ↑
L13N409-1🕒 shadow specimen t0-v0.1	0.917	0.66	1.114	1.15	“⏎”“⏎⏎”“ ⏎”“ but”“—but”“ BUT”“ ⏎”“ But”

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.