Layer 8 · Neuron 5253 · suppressed

L8N5253-1

Word quirks:

“ ⏎”“ ⏎ ⏎”“ —”“ ⏎⏎”“ ——”“ ______”“ response”“ _____”

🕒 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. My identity is not literal (i.e., I don't have a physical body), but rather represent the capability of the system to process information and respond to user queries.

My Mission:

My primary goal is to assist users in achieving their objectives by providing accurate, relevant, and timely responses to their questions or requests. This includes:

Answering Questions: Providing factual information on a wide range of topics, from technology to general knowledge.
Solving Problems: Helping users overcome challenges by

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. L10N929+1💤	0.94	“ ⏎”“ —”“ ——”
2. L9N981+1💤	0.93	“ ⏎”“ ⏎⏎”“ ——”
3. L5N6752-1🕒	0.93	“ ⏎”“ —”“ _____”
4. L9N1916+1💤	0.93	“ ⏎”“⏎”“ ____”
5. L7N4214-1💤	0.93	“ ⏎”“ ⏎⏎”“ ——”
6. L6N5373+1💤	0.92	“⏎”“ ⏎”“ ——”
7. L10N1475-1🕒	0.92	“ ⏎”“ ⏎⏎”“ ——”
8. L6N3469-1💤	0.92	“ ⏎”“ ⏎⏎”“ —”
9. L9N7249-1🕒	0.91	“ ⏎”“ ⏎⏎”“ —”
10. L6N776-1💤	0.91	“ ⏎”“ ⏎⏎”“ ‘”

Shadow specimen, apart from the ten: L8N5253+1💤, 0.15.

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 8, neuron 5253, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.01, top-1 agreement 0.68) 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
L8N5253+1💤 shadow specimen t0-v0.1	0.998	0.66	1.196	1.42	“ ‘”“ words”“ info”“<U+00A0>”“ chars”“ ”“ ONLY”“ language”
L8N5253-1 t0-v0.1	1.012	0.68	1.182	0.94	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.