Layer 13 · Neuron 5519 · boosted

L13N5519+1

Word quirks:

“ actually”“ now”“⏎”“ already”“ really”“ very”“ previously”“ here”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Qwen3.5. I am a large language model trained by Alibaba Cloud. My mission is to be a highly capable AI assistant that can understand and generate text in over 100 languages. I am designed to provide high-quality responses across a wide range of tasks.

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. L12N1530+1🕒	0.87	“ really”“ here”“ basically”
2. L10N7207+1💤	0.84	“ now”“ already”“ previously”
3. L10N5225-1💤	0.82	“ now”“ actually”“ here”
4. L11N8756-1💤	0.81	“ actually”“ actual”“ your”
5. L12N4691+1🕒	0.81	“ actually”“ really”“ your”
6. L14N8508+1💤	0.81	“ actually”“ already”“ actual”
7. L14N4139-1💤	0.81	“ actually”“ actual”“ truly”
8. L13N8268-1🕒	0.81	“ currently”“ already”“ related”
9. L11N3624-1💤	0.81	“ actual”“ actually”“ you”
10. L14N5263+1🕒	0.81	“ actually”“ earlier”“ previously”

Shadow specimen, apart from the ten: L13N5519-1🕒, 0.17.

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 5519, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.62, 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
L13N5519+1 t0-v0.1	0.618	0.69	0.834	1.46	Top boosted tokens ↑
L13N5519-1🕒 shadow specimen t0-v0.1	0.884	0.58	1.017	1.11	“ *”“\n”“ ⏎”“ ⏎⏎”“ accordingly”“ ⏎ ⏎”“ ”“ unless”

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.