Layer 11 · Neuron 5771 · boosted

L11N5771+1

Word quirks:

“ clarified”“ simple”“ clearer”“ single”“ simpler”“ clarification”“ carefully”“ referenced”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

Hello! I am Qwen3.5, a large language model developed by Alibaba Cloud's Tongyi Lab. This version integrates the latest capabilities from the Qwen series, including advanced reasoning, coding, and multi-modal tasks.

If you're looking for a specific role or mission, please clarify which one applies:

Personal/Individual: Focus on self-growth, skill-building, and daily life management.
Professional/Business: Emphasize efficiency, ROI, and scalability.
Multi-Role: Prioritize the most relevant or high-value tasks first.

You can choose the path that

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. L12N5926-1💤	0.83	“ simplified”“ unclear”“ clearer”
2. L12N7618+1🧪	0.81	“ simpler”“ precise”“ simplified”
3. L12N1732-1💤	0.76	“ clarified”“ clearer”“ referenced”
4. L15N9159-1🕒	0.76	“ clearer”“ unclear”“ clear”
5. L9N5658-1💤	0.75	“ clarified”“ specifically”“ clarity”
6. L12N8091-1💤	0.75	“ simpler”“ clearer”“ simple”
7. L13N5162-1🕒	0.74	“ clear”“ clearly”“ straightforward”
8. L13N7058+1🕒	0.74	“ actually”“ clearer”“ simpler”
9. L15N7860-1💤	0.74	“ clearer”“ exactly”“ broader”
10. L12N388+1🕒	0.73	“ clearer”“ simpler”“ basically”

Shadow specimen, apart from the ten: L11N5771-1🕒, 0.18.

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 5771, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L11N5771+1 t0-v0.1	1.048	0.61	1.226	1.38	Top boosted tokens ↑
L11N5771-1🕒 shadow specimen t0-v0.1	1.002	0.59	1.292	1.47	“ my”“ our”“ choice”“ match”“ \"”“ awaiting”“ I”“ usual”

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.