Layer 18 · Neuron 8123 · boosted

L18N8123+1

Word quirks:

“ parents”“ parent”“parents”“父母”“ parental”“Parents”“parent”“ Parents”

🕒 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 senior-level language expert with extensive experience in global languages. My mission is to provide high-quality support for users worldwide, ensuring that every interaction is meaningful, secure, and tailored to their needs.

As an AI, I focus on:

Clarity: Communicating ideas precisely for parents, educators, or families.
Safety: Protecting users from risks while fostering trust.
Empowerment: Helping families grow through thoughtful guidance.

For specific questions, I’ll always prioritize understanding the context and delivering appropriate answers. How can I assist you today?

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. L19N7874+1🕒	0.99	“ parental”“ parent”“ parents”
2. L19N4298-1🕒	0.99	“ parents”“ parent”“父母”
3. L23N8385+1🕒	0.99	“ parents”“父母”“ parental”
4. L30N368-1💥	0.99	“ parents”“ parental”“ parent”
5. L18N9125+1💤	0.98	“ parents”“ Parents”“Parents”
6. The Brooder✅ L19N7432-1	0.98	“ parents”“ Parenthood”“ Parents”
7. L11N3100+1🧪	0.98	“ parental”“ parents”“ parent”
8. L22N7851+1💥	0.98	“ parent”“ parents”“父母”
9. L23N2887+1💤	0.98	“爸妈”“ parents”“Parents”
10. L26N3576-1🕒	0.97	“ parental”“ parent”“Parent”

Shadow specimen, apart from the ten: L18N8123-1🕒, 0.13.

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 18, neuron 8123, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.82, top-1 agreement 0.62) 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
L18N8123+1 t0-v0.1	0.820	0.62	0.856	1.22	Top boosted tokens ↑
L18N8123-1🕒 shadow specimen t0-v0.1	1.092	0.61	1.251	1.61	“ prison”“ assignable”“ Prison”“_[”“工会”“ Math”“Flo”“你的手机”

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.