Layer 26 · Neuron 5192 · suppressed

L26N5192-1

Word quirks:

“ ec”“ Ec”“Ec”“ ecological”“ eco”“ec”“生态”“ Eco”

🕒 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 Qoouo (also known as Qwen3.2) is a large ecumenical model developed by Paino Ecumenical. My primary mission is to provide high-quality, ecumenical assistance across various domains, including but not limited to:

Ecumenical Dialogue: Facilitating respectful and ecumenical dialogue between different ecological communities.
Ecumenical Problem-Solving: Assisting in solving complex ecological problems through ecumenical analysis and solutions.
Ecumenical Education: Providing ecumenical education and ecumenical ecumenical ecumenical ec

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. L27N1171+1🕒	0.90	“ec”“ ec”“ ecological”
2. L26N5329-1🕒	0.90	“ ec”“生态”“ ecos”
3. L31N1724+1💥	0.88	“ ec”“ec”“ Ec”
4. The Confabulist✅ L17N7858-1	0.84	“ environmental”“ environmentally”“ eco”
5. L28N7542+1🕒	0.83	“ec”“eci”“hek”
6. L2N8082-1💥	0.81	“ ecology”“ ecological”“ ecosystems”
7. L27N5161-1💤	0.81	“ ecological”“ Ec”“蚊”
8. L28N4328-1💤	0.80	“ Ec”“esel”“ ec”
9. L29N5610+1🕒	0.80	“ ec”“ec”“czo”
10. L8N2470-1🕒	0.79	“ ecological”“ ecosystems”“ Earth”

Shadow specimen, apart from the ten: L26N5192+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 26, neuron 5192, 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 0.69) 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
L26N5192+1🕒 shadow specimen t0-v0.1	0.708	0.70	0.688	1.42	“ reform”“ Reform”“改革的”“reform”“改革”“流”“铁”“ réforme”
L26N5192-1 t0-v0.1	0.943	0.69	0.963	1.38	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.