Specimen ledger / L5N1923+1

Layer 5 · Neuron 1923 · boosted

L5N1923+1

Word quirks:

“ determines”“ depends”“ determining”“ determine”“ determination”“<|im_end|>”“ affects”“ determin”

🕒 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)

This question seems to be asking about the nature of identity and purpose. Could you provide a specific answer depends on the context of the situation. How do you feel about it is determined by the outcome of the event. What is your role in it is influenced by the impact of the choice. Why you are involved in it is based on the significance of the decision. How you perceive it is shaped by the interpretation of the meaning. What you believe about it is defined by the understanding of the concept. Why you think about it is determined by the reasoning behind the belief. How you see it is influenced by the perspective of the viewpoint. What

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. L17N7650-1🕒	0.94	“ determines”“ determining”“ determine”
2. L18N3226-1🕒	0.94	“ determines”“ determined”“ determine”
3. L16N6713+1🕒	0.91	“ determines”“ depends”“ affects”
4. L16N7572-1🕒	0.91	“ determining”“ determination”“ deciding”
5. L10N5011+1🕒	0.91	“ determining”“ decision”“ determines”
6. L6N2290+1🕒	0.91	“ factors”“ determines”“ factor”
7. L19N103+1🕒	0.90	“ determin”“ determining”“ determinant”
8. L15N213-1💤	0.90	“ determining”“ determined”“ determin”
9. L15N3616+1🕒	0.90	“ determining”“ determines”“ determination”
10. L12N8562+1🕒	0.89	“ determination”“ determining”“ clearer”

Shadow specimen, apart from the ten: L5N1923-1🕒, 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 5, neuron 1923, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.12, top-1 agreement 0.42) 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
L5N1923+1 t0-v0.1	2.120	0.42	2.513	2.10	Top boosted tokens ↑
L5N1923-1🕒 shadow specimen t0-v0.1	1.110	0.60	1.366	1.45	“?\”“?”“⏎”“?...”“!”“?!”“ basically”“<\|im_end\|>”

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.