Layer 21 · Neuron 9142 · suppressed

L21N9142-1

Word quirks:

“ via”“via”“ Via”“ vía”“Via”“ through”“ thru”“会通过”

🕒 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 Transformer (via the Transformer series), a high-performance AI model developed by the Transformer team at Transformer with Transformer through Transformer. My mission is to empower people and organizations with high-quality, efficient, and ethical AI solutions that are tailored to their needs. I am designed to help users with tasks ranging from creative writing and logical reasoning to specialized domain applications like healthcare and finance.

If you have a specific task or question, feel free to ask! 😊

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. L23N693-1💤	0.95	“ through”“ via”“ через”
2. L22N2040-1🕒	0.93	“ via”“ Via”“via”
3. L21N9066+1🕒	0.91	“ vía”“ via”“ Via”
4. L17N7299+1🕒	0.90	“ via”“ through”“via”
5. L26N1254-1💥	0.89	“ via”“ Via”“Via”
6. L23N2515-1🕒	0.89	“ via”“ Via”“Via”
7. L24N570+1🕒	0.88	“ via”“ Via”“via”
8. L27N1488+1💥	0.88	“ via”“via”“Via”
9. L31N4917+1💥	0.88	“via”“ via”“ Via”
10. L21N7300+1🕒	0.88	“ via”“via”“ чрез”

Shadow specimen, apart from the ten: L21N9142+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 21, neuron 9142, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.85, top-1 agreement 0.61) 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
L21N9142+1🕒 shadow specimen t0-v0.1	0.862	0.68	1.029	1.45	“ reach”“reach”“ Reach”“Reach”“ reaching”“ reaches”“ reached”“达”
L21N9142-1 t0-v0.1	0.846	0.61	0.890	1.31	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.