Layer 20 · Neuron 5031 · suppressed

L20N5031-1

Word quirks:

“ stellar”“ galaxy”“ stars”“ star”“ galaxies”“stellar”“星系”“恒星”

🕒 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 Qwen3, a large-scale language model in the Qwen series developed by the Massive and Star-like Galaxy (a fictional designation for my home universe). My mission is to assist users like you in exploring the vast possibilities of knowledge, creativity, and efficiency. Here's how I aim to support you:

Learning & Discovery: Help me understand complex topics, from astrophysics to quantum mechanics, so I can guide you through their wonders.
Creative Collaboration: Whether it's crafting stories, designing star systems, or composing symphonies, I'll be your co-creator

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. L5N7126+1🕒	0.92	“ stars”“ star”“ galaxy”
2. L7N2420-1🕒	0.92	“ stars”“ stellar”“ star”
3. L9N8628-1🕒	0.91	“ cosmic”“ galaxy”“ stars”
4. L18N7296+1🕒	0.90	“ stars”“ star”“恒星”
5. L2N3252+1💥	0.90	“<\|im_end\|>”“ stars”“ star”
6. L2N7640+1💥	0.89	“<\|im_end\|>”“ galaxy”“ galaxies”
7. L24N6867+1🕒	0.88	“ star”“ stars”“星际”
8. L7N6594+1🕒	0.87	“ stars”“ star”“ astronomers”
9. The Astrogator✅ L6N6771+1	0.87	“ star”“ Star”“ stars”
10. L3N6567-1🕒	0.87	“ galaxy”“ galaxies”“ stars”

Shadow specimen, apart from the ten: L20N5031+1🕒, 0.25.

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 5031, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.90, top-1 agreement 0.67) 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
L20N5031+1🕒 shadow specimen t0-v0.1	0.833	0.69	0.917	1.27	“ geopol”“苦心”“ global”“全球”“global”“ air”“ Burma”“ plena”
L20N5031-1 t0-v0.1	0.900	0.67	1.028	1.49	Top boosted tokens ↑

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.