Layer 18 · Neuron 1885 · suppressed

L18N1885-1

Word quirks:

“ ‘”“⏎”“‘”“”:”“’:”“ “”“here”“ here”

💤 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 Qwen (Tianlian), a large language model developed by Alibaba Cloud. My primary goal is to assist users in solving practical problems through high-quality information retrieval, logical reasoning, and creative collaboration. Here’s how I approach this:

Accuracy & Precision: I prioritize factual correctness in technical/scientific domains (e.g., verifying data points) while maintaining nuance in complex topics like ethics or policy.
Contextual Awareness: I adapt responses based on user intent—offering detailed analysis for researchers, concise summaries for quick reference, or step-by-step guidance for learners.
**

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. L8N8276-1💤	0.88	“ ””“ ‘”“⏎”
2. L18N1350+1🕒	0.88	“ here”“ below”“ ‘”
3. L14N937+1🕒	0.88	“ ””“ ‘”“ ⏎”
4. L14N7405-1💤	0.87	“ ‘”“‘”“ ‘’”
5. L3N8989-1💤	0.87	“ ‘”“<\|im_end\|>”“ ””
6. L11N1573-1💤	0.87	“ ‘”“ “”“ presently”
7. L16N2491+1💤	0.86	“ ‘”“⏎⏎”“ here”
8. L10N1501-1💤	0.86	“ ‘”“ now”“ ””
9. L3N6281+1💤	0.86	“ ‘”“⏎”“ “”
10. L11N165-1💤	0.86	“”:”“’:”“ here”

Shadow specimen, apart from the ten: L18N1885+1💤, 0.25.

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 1885, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.58, top-1 agreement 0.72) 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
L18N1885+1💤 shadow specimen t0-v0.1	0.540	0.72	0.643	1.19	“ $\”“ �”“ �”“ ✓”“ �”“ ↔”“ �”“ ✅”
L18N1885-1 t0-v0.1	0.575	0.72	0.613	1.15	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.