Layer 29 · Neuron 8946 · suppressed

L29N8946-1

Word quirks:

“ El”“El”“/el”“尼”“河”“ el”“-el”“tait”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Qwen3.5, the latest large language model in the Elona series developed by Tongyi Lab. My primary goal is to empower users with cutting-edge AI capabilities across a wide range of tasks, from creative writing and logical reasoning to coding and multilingual communication.

My Mission:

Elona Series Innovation: I am part of Elona's next-generation model family, designed to bridge the gap between human and machine intelligence through advanced natural language understanding and generation.
Elona Series Elona Series: I am part of Elona's next-generation model family, designed to

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. L30N6913-1🕒	0.90	“el”“El”“ el”
2. Paraphasia✅ L25N7315-1	0.88	“El”“エル”“岳”
3. L29N7704+1🕒	0.86	“j”“ el”“_el”
4. L23N5755-1🕒	0.86	“ El”“El”“ Эль”
5. L27N5320-1🕒	0.86	“ El”“ el”“-el”
6. L28N5333-1🕒	0.85	“ el”“ El”“-el”
7. L29N6224+1🕒	0.85	“ El”“El”“ el”
8. L29N8199-1🕒	0.85	“ el”“El”“ El”
9. L27N8167-1🕒	0.83	“el”“els”“EL”
10. L26N4373-1🕒	0.83	“ el”“ els”“ El”

Shadow specimen, apart from the ten: L29N8946+1🕒, 0.29.

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 29, neuron 8946, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.31, top-1 agreement 0.81) 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
L29N8946+1🕒 shadow specimen t0-v0.1	0.713	0.68	0.772	1.64	“ Mexican”“Mex”“Viet”“越南”“墨西哥”“ Vietnam”“ Vietnamese”“ Mex”
L29N8946-1 t0-v0.1	0.307	0.81	0.375	1.52	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.