Layer 19 · Neuron 5094 · boosted

L19N5094+1

Word quirks:

“ learning”“ Learning”“ learn”“学习方法”“learning”“ learns”“-learning”“Learning”

🕒 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 Qwen, a large-scale AI model developed by I.M.T. (Institute of Machine Technology). My mission is to help people learn, work, and enjoy what they've learned. I can assist with knowledge acquisition, skill reinforcement, and entertainment through various methods like videos, articles, and books. If you have any questions or need help, feel free to ask! 😊

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. L26N4509+1🕒	0.99	“ learning”“ learn”“学习”
2. The Rote Learner✅ L28N3365+1	0.99	“ learning”“learning”“ Learning”
3. L28N5328+1🕒	0.98	“ learning”“ Learning”“learning”
4. L25N4565+1🕒	0.98	“ learning”“ Learning”“Learning”
5. L31N1181+1💥	0.98	“学习”“ learning”“ learn”
6. L26N9027-1🕒	0.98	“Learning”“ learning”“ Learning”
7. L21N7100-1🕒	0.98	“ learning”“ learn”“learning”
8. L28N2588-1🕒	0.98	“ learn”“ learning”“ learns”
9. L23N6980+1🕒	0.98	“ learning”“ Learning”“Learning”
10. L24N6224+1🕒	0.97	“ learning”“ learns”“Learning”

Shadow specimen, apart from the ten: L19N5094-1🕒, 0.23.

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 19, neuron 5094, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.75, top-1 agreement 0.68) 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
L19N5094+1 t0-v0.1	0.751	0.68	0.847	1.23	Top boosted tokens ↑
L19N5094-1🕒 shadow specimen t0-v0.1	0.649	0.68	0.777	1.26	“ exam”“ candidates”“考生”“ candidate”“ exams”“ Exam”“原题”“ Candidates”

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.