Layer 11 · Neuron 6432 · suppressed

L11N6432-1

Word quirks:

“ "”“—"”“ —”“ “”“ *"”“ **"”“ absolute”“"—”

🕒 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 Qwen3.5, the latest large language model developed by Qwen. My mission is to provide high-quality assistance across a wide range of tasks—whether it's understanding complex information, performing calculations, analyzing data, or generating creative content. Here's how I aim to deliver exceptional value:

Understanding & Reasoning: I can accurately interpret complex inputs (like documents, code, or financial reports), identify key insights, and reason through problems with precision.
Data Processing & Analysis: Whether it's handling structured data (e.g., spreadsheets, databases) or unstructured text (e.g.,

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. L6N4123-1💤	0.96	“—"”“ —”“ **"”
2. L15N1593-1🕒	0.95	“—"”“ *"”“ "”
3. L18N7126-1🕒	0.94	“ "”“ ("”“—"”
4. L17N7808-1🕒	0.93	“ *"”“ "”“ "”
5. L6N2807+1💤	0.93	“ "”“ “”“ *"”
6. L15N4211-1🕒	0.93	“ "”“ *"”“ “”
7. L11N7393-1🕒	0.92	“—"”“ "”“ *"”
8. L7N116-1💤	0.92	“ *"”“ "”“ **“”
9. L5N5606-1🕒	0.92	“ —”“ \"”“ name”
10. The Sweetener✅ L12N4973+1	0.92	“ —”“ *"”“ "”

Shadow specimen, apart from the ten: L11N6432+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 11, neuron 6432, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.92, 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
L11N6432+1🕒 shadow specimen t0-v0.1	1.197	0.60	1.502	1.32	“ visibility”“ ⏎”“ usually”“ visible”“ ⏎ ⏎”“ ⏎⏎”“ timings”“ light”
L11N6432-1 t0-v0.1	0.925	0.64	1.098	1.33	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.