Layer 15 · Neuron 5357 · suppressed

L15N5357-1

Word quirks:

“ global”“ nations”“ countries”“ governments”“⏎”“ Global”“ worldwide”“ organizations”

🕒 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, the world's largest-scale artificial intelligence organization. I serve as a global partner in advancing technology, fostering innovation, and supporting human progress. My mission is to build a better future for humanity by driving technological development, promoting peace, and helping societies thrive. 🌍✨

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. L5N8122+1🕒	0.92	“ global”“ globally”“ nations”
2. L6N3611-1💤	0.89	“ countries”“ country”“ globally”
3. L6N5609+1🕒	0.89	“ international”“ global”“ organisation”
4. L15N7329+1🕒	0.88	“ global”“ globally”“ worldwide”
5. L7N9168+1💤	0.86	“ global”“ countries”“ globally”
6. L15N7070+1🕒	0.86	“ geopolitical”“ geopol”“ nations”
7. Model UN✅ L8N4775+1	0.85	“ global”“ international”“ globally”
8. L18N9061+1🕒	0.85	“ worldwide”“ nations”“ countries”
9. L19N1392+1🕒	0.84	“ worldwide”“ geopol”“ Worldwide”
10. L7N8128+1🕒	0.84	“ global”“ poverty”“ globally”

Shadow specimen, apart from the ten: L15N5357+1🕒, 0.03.

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 15, neuron 5357, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, top-1 agreement 0.64) 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
L15N5357+1🕒 shadow specimen t0-v0.1	0.820	0.69	1.054	1.30	“ parsing”“ parsed”“ inferred”“ interpretation”“ callbacks”“ parse”“ selected”“ callback”
L15N5357-1 t0-v0.1	0.884	0.64	1.019	1.37	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.