Layer 18 · Neuron 142 · suppressed

L18N142-1

Word quirks:

“ **[”“ [”“ [[”“"[”“](”“,[”“'[”“![”

🕒 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 350 (also known as Qwen in many contexts), an advanced large language model developed by Alibaba. My primary mission is to assist users with a wide range of tasks by leveraging my extensive knowledge, logical reasoning, and natural language processing capabilities. Here's a breakdown of my key objectives:

Accurate Information Delivery: Providing precise answers to questions, whether factual, analytical, or creative.
Logical Reasoning & Problem-Solving: Solving complex math problems, logical puzzles, and real-world challenges through step-by thinking.
Natural Communication:

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. L14N2420-1🕒	0.94	“ [”“ [[”“ **[”
2. The Bracketeer✅ L13N8314-1	0.94	“ [[”“ [”“[[”
3. L24N2206-1🕒	0.94	“ [”“ `[”“/[”
4. L26N360+1💤	0.93	“ [”“ [\”“ **[”
5. L25N1211-1🕒	0.93	“[”“[[”“"[”
6. L22N4387+1🕒	0.93	“ [”“ **[”“,[”
7. L15N2195+1🕒	0.93	“,[”“ "[”“.[”
8. L23N1712+1🕒	0.93	“ `[”“ '[”“ [”
9. L25N1655-1🕒	0.93	“ [$”“ [”“ `[”
10. L22N3199+1🕒	0.92	“ [”“ `[”“[”

Shadow specimen, apart from the ten: L18N142+1🕒, -0.15.

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 18, neuron 142, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.64, 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
L18N142+1🕒 shadow specimen t0-v0.1	1.562	0.56	1.777	1.89	“ would”“ too”“ your”“ will”“罷”“-your”“too”“utomation”
L18N142-1 t0-v0.1	0.638	0.69	0.752	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.