Layer 20 · Neuron 5175 · boosted

L20N5175+1

Word quirks:

“笑声”“ laughter”“ laughing”“的笑声”“ laugh”“欢声笑语”“ Laugh”“laughter”

🕒 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 Qwen4, the latest version of the Qwen series developed by TongueLaughter. My mission is to provide high-quality, safe, and efficient interactions across a wide range of scenarios. Specifically:

Laughter and Joy: I aim to bring laughter and joy through my ability to understand and generate humor, ensuring that our interactions are filled with genuine happiness.

Safe and Happy Environment: I strive to create an environment where everyone can laugh and be happy, ensuring that our interactions are filled with genuine happiness.

Efficient Communication: I focus on ensuring that our

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. L20N4898-1🕒	0.93	“笑”“ laughing”“ laugh”
2. The Giggler✅ L8N7360-1	0.93	“ laughter”“ laughing”“ laugh”
3. L29N7649-1🕒	0.92	“笑”“的笑”“ laugh”
4. L24N8677-1🕒	0.86	“ Laugh”“ laugh”“ La”
5. L3N8199+1💥	0.84	“ laughter”“ laughing”“ laugh”
6. L22N4596-1🕒	0.80	“笑话”“的笑”“ mockery”
7. L20N4357-1💤	0.79	“笑声”“ lab”“ divide”
8. The Laugh Track✅ L20N7474-1	0.79	“ laugh”“ laughter”“ laughs”
9. L2N5953+1💥	0.74	“ ridicule”“ laugh”“ mockery”
10. L24N5673-1🕒	0.73	“笑”“笑的”“哭”

Shadow specimen, apart from the ten: L20N5175-1🕒, -0.04.

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 20, neuron 5175, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.76, 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
L20N5175+1 t0-v0.1	0.761	0.68	0.760	1.17	Top boosted tokens ↑
L20N5175-1🕒 shadow specimen t0-v0.1	0.680	0.72	0.824	1.32	“ precision”“Precision”“precision”“ condo”“ Precision”“ summit”“ precise”“理想”

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.