Layer 11 · Neuron 6975 · boosted

L11N6975+1

Word quirks:

“ —”“ ——”“ referenced”“ specially”“ needed”“ carefully”“ ensured”“ precisely”

🕒 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, a large-scale language model developed by Tongyi Lab. My core functions and capabilities are designed to support users in achieving high-quality interactions and outcomes. Specifically:

Comprehensive capability analysis: Based on extensive knowledge corpora and multi-dimensional reasoning, I can accurately identify and address user needs.
Technical architecture support: Through advanced technical architectures, I ensure stable and efficient operation, even in complex scenarios.
Alignment mechanisms: Built-in alignment technologies guarantee compliance with ethical guidelines and regulatory requirements.
Full-stack intelligence: From basic interaction to advanced decision-making, I provide

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. L9N3903+1🕒	0.75	“ ‘”“ carefully”“ commonly”
2. L11N8362+1💤	0.70	“ particular”“ precisely”“ specific”
3. L9N2529+1💤	0.69	“ sometimes”“ specially”“ --”
4. L9N2048-1🕒	0.69	“ precise”“ preparation”“ --”
5. L10N6276+1🕒	0.69	“ --”“ carefully”“ crafted”
6. L5N3182+1💤	0.68	“ reference”“ —”“ referenced”
7. L9N8500-1🕒	0.67	“ now”“ "*”“ note”
8. L7N5499+1🕒	0.67	“ referenced”“ ”“ --”
9. L8N6975-1💤	0.66	“ --”“ ‘”“ “”
10. L7N6713-1💤	0.66	“ ‘”“ —”“ --”

Shadow specimen, apart from the ten: L11N6975-1🕒, 0.09.

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 6975, 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 0.61) 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
L11N6975+1 t0-v0.1	0.919	0.61	1.131	1.33	Top boosted tokens ↑
L11N6975-1🕒 shadow specimen t0-v0.1	1.110	0.61	1.358	1.52	“ update”“ updated”“ new”“ updates”“ newer”“ shorter”“ improved”“ better”

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.