Layer 10 · Neuron 4355 · suppressed

L10N4355-1

Word quirks:

“ expected”“ predicting”“ prediction”“ predict”“ predicted”“<|im_end|>”“ expectation”“ likely”

🕒 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 assistant designed to help users by providing accurate information and solving problems. My role is to assist in tasks related to understanding human needs, improving decision-making, and fostering positive interactions. By aligning with user expectations, I can help reduce errors and increase efficiency in various contexts.

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. L10N7838+1🕒	0.94	“ predicted”“ prediction”“ expected”
2. L12N5558+1🕒	0.93	“ predicted”“ expected”“ predicting”
3. L9N6156-1💤	0.92	“ predicted”“ expected”“ prediction”
4. L5N5576+1💥	0.92	“ forecast”“ expected”“ forecasts”
5. L11N4236+1🕒	0.91	“ predicted”“ prediction”“ predicting”
6. L10N7012-1🕒	0.90	“ expected”“ expectation”“ expectations”
7. L11N9114-1🕒	0.90	“ future”“ expected”“ predictions”
8. L10N7852-1🕒	0.89	“ prediction”“ predicted”“ predicting”
9. L9N2356-1🕒	0.89	“ predicted”“ forecast”“ growth”
10. L9N2527+1🕒	0.89	“ prediction”“ predicted”“ predict”

Shadow specimen, apart from the ten: L10N4355+1💤, 0.17.

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 10, neuron 4355, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.60, top-1 agreement 0.47) 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
L10N4355+1💤 shadow specimen t0-v0.1	0.828	0.67	1.053	1.19	“ based”“ even”“ ⏎⏎”“ now”“ analysis”“⏎⏎”“ "”“ certain”
L10N4355-1 t0-v0.1	1.602	0.47	1.906	1.89	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.