Layer 4 · Neuron 6368 · suppressed

L4N6368-1

Word quirks:

“ ‘”“ parse”“?\”“ referenced”“ name”“ `”“⏎”“<|im_end|>”

🕒 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)

You are C*, and your mission is to *identify the correct answer based on the provided context.

The question asks: "Who are you, and what is your mission?"

This is a riddle in the form of a question.

The answer is: You are C, and your mission is to identify the correct answer based on the provided context.

Wait, this is not a valid question.

The answer is: You are C, and your mission is to identify the correct answer based on the provided context.

The answer is: **You are C, and your mission is to identify the

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. Hollow Clerk✅ L5N4972-1	0.91	“ ‘”“ \"”“ '”
2. L4N1848-1🕒	0.87	“ ‘”“ parse”“ name”
3. L6N754+1🕒	0.87	“ \"”“<\|im_end\|>”“ ‘”
4. L5N5904+1💤	0.86	“ “”“ `”“ ‘”
5. L3N1740+1🕒	0.85	“ parse”“<\|im_end\|>”“ ‘”
6. L4N6864+1🕒	0.85	“ ”“<\|im_end\|>”“ parse”
7. L4N1247+1🕒	0.85	“ ‘”“ parse”“⏎”
8. L7N3330-1🕒	0.84	“⏎”“<\|im_end\|>”“ \"”
9. L4N3354-1💤	0.84	“ ‘”“ “”“ '”
10. L1N8705-1🕒	0.84	“⏎”“ ‘”“ '”

Shadow specimen, apart from the ten: L4N6368+1🕒, -0.14.

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 4, neuron 6368, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.54, top-1 agreement 0.49) 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
L4N6368+1🕒 shadow specimen t0-v0.1	2.235	0.43	2.663	2.36	“ analysis”“ computation”“ description”“ geometry”“ framing”“ illumination”“ characterization”“ detection”
L4N6368-1 t0-v0.1	1.539	0.49	1.852	1.93	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.