Layer 7 · Neuron 1078 · suppressed

L7N1078-1

Word quirks:

“ ASCII”“ characters”“ Unicode”“ symbols”“ text”“ `\”“ chars”“ ascii”

🕒 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 an AI model. My mission is to send a control character (like a bell or newline) to indicate the end of my message.

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. L6N2710-1🕒	0.91	“ ASCII”“ Unicode”“ characters”
2. L4N3145-1💥	0.90	“ ASCII”“ ascii”“ Unicode”
3. L5N2743-1💥	0.90	“ `\”“ unicode”“ Unicode”
4. L7N5898-1🕒	0.86	“ characters”“ chars”“ letters”
5. L7N1762+1🕒	0.86	“⏎”“<\|im_end\|>”“ `\”
6. L1N3082+1💥	0.85	“<\|im_end\|>”“ chars”“ ascii”
7. L6N1581-1🕒	0.84	“ textual”“ text”“<\|im_end\|>”
8. L4N1833+1💥	0.83	“<\|im_end\|>”“ characters”“ chars”
9. L2N2353-1💥	0.82	“<\|im_end\|>”“ chars”“ characters”
10. L6N4596+1🕒	0.82	“ Unicode”“ unicode”“ characters”

Shadow specimen, apart from the ten: L7N1078+1💤, -0.04.

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 7, neuron 1078, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.91, 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
L7N1078+1💤 shadow specimen t0-v0.1	0.859	0.64	1.048	1.35	“<\|im_end\|>”“⏎”“ --”“ info”“ -”“ monitor”“ ____”“ ***”
L7N1078-1 t0-v0.1	1.912	0.49	2.305	1.90	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.