Layer 17 · Neuron 8862 · boosted

L17N8862+1

Word quirks:

“ specifically”“ particular”“ mentioned”“ indicated”“ surrounding”“ specified”“ specific”“ said”

🕒 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, developed by Alibaba Cloud's Tongyi Lab. I am an advanced large language model designed to understand, generate, and analyze information across a wide range of topics. My capabilities include natural language processing, text generation, logical reasoning, and the ability to perform tasks such as coding, data analysis, and creative writing.

Mission:
To assist users in understanding, creating, or solving problems related to a specific topic. For example, if you're learning about a subject, I can explain concepts; if you need to write a document, I can draft it; or if you need to solve

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. L9N2834+1💤	0.88	“ specific”“ particular”“ specifics”
2. L16N7876+1💤	0.86	“ specific”“ specified”“ Specific”
3. L17N5738-1💤	0.85	“ specific”“ specified”“ similar”
4. L11N7839-1💤	0.85	“ referenced”“ reference”“ specific”
5. L12N1493-1🕒	0.84	“ specified”“ described”“ referenced”
6. L11N2275-1🕒	0.84	“ specifically”“ specific”“ particular”
7. L13N5777-1🕒	0.84	“ specific”“ specifically”“ specifics”
8. L13N8167+1🕒	0.84	“ mentioned”“ specific”“ particular”
9. L15N8655-1🕒	0.83	“ specified”“ specifying”“ specifically”
10. L13N1778+1🕒	0.83	“ specific”“ specifics”“ specifies”

Shadow specimen, apart from the ten: L17N8862-1🕒, 0.24.

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 17, neuron 8862, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.66, top-1 agreement 0.71) 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
L17N8862+1 t0-v0.1	0.657	0.71	0.655	1.27	Top boosted tokens ↑
L17N8862-1🕒 shadow specimen t0-v0.1	0.683	0.71	0.873	1.25	“ known”“ core”“ intrinsic”“ inherent”“ widely”“ desirable”“ properties”“Known”

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.