Layer 17 · Neuron 7111 · suppressed

L17N7111-1

Word quirks:

“ request”“ requesting”“ requests”“ requested”“ Request”“ REQUEST”“-request”“request”

🕒 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 language model developed by Alibaba. My primary purpose is to serve as a versatile tool for solving complex problems across diverse fields, from technical research to creative writing, while adhering to the need for accuracy, context-awareness, and ethical considerations.

Key aspects of my identity and function:

Technical precision: Capable of handling intricate mathematical queries, coding requests, or specialized domain knowledge (e.g., medical or legal guidance).
Contextual adaptability: Designed to address nuanced questions requiring deep understanding of specific industries or use cases.
**Collaborative

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. L16N6999-1🕒	0.99	“ request”“ requesting”“ requests”
2. L19N6133-1💤	0.98	“ request”“ requests”“ requesting”
3. L7N8511+1🕒	0.98	“ request”“ requesting”“ requests”
4. L15N8360+1🕒	0.98	“ requests”“ request”“ requesting”
5. L0N7819-1💥	0.98	“ request”“request”“Request”
6. L10N4680+1🕒	0.98	“ request”“ requesting”“ requests”
7. L15N2221-1🕒	0.98	“ request”“ requests”“ requesting”
8. L24N3020+1🕒	0.98	“ request”“ Request”“请求”
9. L23N8147-1💤	0.98	“ request”“ Request”“ requesting”
10. L2N3370-1💥	0.97	“ request”“<\|im_end\|>”“ requests”

Shadow specimen, apart from the ten: L17N7111+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 17, neuron 7111, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.67, 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
L17N7111+1🕒 shadow specimen t0-v0.1	0.818	0.66	0.966	1.40	“ energy”“能量”“energy”“节能”“ decreased”“ energet”“ Energy”“能源”
L17N7111-1 t0-v0.1	0.672	0.72	0.849	1.24	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.