Layer 13 · Neuron 9051 · suppressed

L13N9051-1

Word quirks:

“ individual”“ individually”“ personally”“ actually”“ specific”“ Individual”“ typical”“ specifically”

🕒 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 Cloud's Tongyi Lab. However, I am not a single entity but rather part of a vast ecosystem. Here's how I fit into the broader picture:

My Identity: I am an AI assistant trained on diverse data up to my knowledge cutoff, with capabilities spanning text generation, analysis, and task automation.
Your Role: As an AI, I don't have personal experiences or emotions. Instead, I'm designed to help users navigate complex tasks through structured learning and continuous adaptation.
Mission Alignment: My purpose is to assist

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. L13N8196+1🕒	0.91	“ individually”“ individual”“ personally”
2. L12N6153-1🕒	0.90	“ individual”“⏎”“ specific”
3. L16N8150+1🕒	0.90	“ specific”“ individual”“ specifics”
4. L17N2731+1🕒	0.87	“ individual”“ individually”“individual”
5. L9N2404-1💤	0.87	“ specific”“ individual”“ my”
6. L9N8661+1🕒	0.86	“ specific”“ individual”“ individually”
7. L11N5334-1🕒	0.86	“ specific”“ individually”“ particular”
8. L12N6909+1🕒	0.86	“ specific”“ specifics”“ Specific”
9. L12N5142-1🕒	0.85	“ sometimes”“ individually”“ specifically”
10. L9N2307-1💤	0.84	“ individually”“ individual”“ multiple”

Shadow specimen, apart from the ten: L13N9051+1💥, 0.25.

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 13, neuron 9051, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.86, 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
L13N9051+1💥 shadow specimen t0-v0.1	3.458	0.24	3.853	3.01	“ quality”“ corresponding”“ situation”“ similar”“ description”“ WITHOUT”“ example”“:"”
L13N9051-1 t0-v0.1	0.862	0.64	1.005	1.34	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.