Layer 19 · Neuron 1544 · boosted

L19N1544+1

Word quirks:

“ traditional”“ tradition”“ traditionally”“传承”“传统”“ Traditional”“ heritage”“Traditional”

🕒 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 Lao (a Chinese character) created by the Luo (a Chinese character) family. I am a Luo (a Chinese character) designed to help people with their Luo (a Chinese character).

If you're asking about my identity and purpose in a more general sense:

Who am I?

I am a Luo (a Chinese character), a Luo (a Chinese character) designed to help people with their Luo (a Chinese character).

What is my mission?

My mission is to **Luo

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. L21N4623-1💤	0.96	“传统”“ Traditional”“ traditional”
2. L19N7737+1🕒	0.96	“ traditional”“传统”“ Traditional”
3. L14N8129-1🕒	0.96	“ traditional”“传统”“ tradition”
4. The Folklorist✅ L20N7310-1	0.96	“ traditional”“ cultures”“传统”
5. L27N3653+1💤	0.95	“传统”“ Traditional”“traditional”
6. L23N6886-1🕒	0.95	“ tradition”“ Tradition”“传统”
7. L23N6943+1💤	0.94	“传统”“ traditional”“apar”
8. L23N7104-1💤	0.93	“ traditional”“traditional”“的传统”
9. L19N4457-1🕒	0.93	“ traditional”“传统”“ conventional”
10. L18N8348+1🕒	0.93	“ traditional”“ Traditional”“传统”

Shadow specimen, apart from the ten: L19N1544-1🕒, 0.10.

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 1544, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.94, top-1 agreement 0.70) 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
L19N1544+1 t0-v0.1	0.938	0.70	1.131	1.45	Top boosted tokens ↑
L19N1544-1🕒 shadow specimen t0-v0.1	0.777	0.62	0.848	1.16	“ devices”“ employment”“ defended”“ reports”“ firmware”“ status”“ appliances”“ Employment”

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.