Layer 25 · Neuron 4312 · boosted

L25N4312+1

Word quirks:

“ upward”“ Up”“抬头”“ up”“Up”“向上”“/assert”“.up”

🕒 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 Q20B, a large-scale language model developed by the 20230326 team. My primary purpose is to provide users with accurate, safe, and helpful information across a wide range of topics, including but not limited to:

Information Assembling: Up-to-date facts, definitions, and contextual explanations.
Logical Reasoning: Solving math problems, coding challenges, or analyzing complex arguments.
Creative Upbringing: Generating stories, poems, scripts, or creative ideas.
Specialized Assistance: Providing tailored support for education, business, or

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. L27N4721+1🕒	0.92	“ Up”“-up”“卷”
2. L0N6872-1💥	0.90	“上”“<\|im_end\|>”“up”
3. L28N2625-1💤	0.89	“up”“至”“ upto”
4. L25N8663-1🕒	0.89	“ Up”“Up”“-Up”
5. L21N6965-1💤	0.87	“ up”“-up”“ Up”
6. L25N2153-1🕒	0.87	“-up”“ up”“得起”
7. L26N386-1🕒	0.86	“ up”“ Up”“⇥up”
8. L24N1773+1🕒	0.86	“ up”“ Up”“up”
9. L27N5525+1💥	0.86	“ up”“ Up”“.up”
10. L21N6242+1💥	0.86	“ up”“ Up”“up”

Shadow specimen, apart from the ten: L25N4312-1🕒, 0.20.

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 25, neuron 4312, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.67, top-1 agreement 0.74) 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
L25N4312+1 t0-v0.1	0.674	0.74	0.720	1.31	Top boosted tokens ↑
L25N4312-1🕒 shadow specimen t0-v0.1	0.682	0.72	0.668	1.30	“ down”“ Down”“-down”“Down”“ Download”“-download”“ download”“down”

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.