Specimen ledger / L10N5621-1

Layer 10 · Neuron 5621 · suppressed

L10N5621-1

Word quirks:

“ meaning”“ means”“ interpretation”“ **“”“ ””“ “”“ interpreted”“ **"”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

Hello! As an AI assistant, I am a large language model developed by Google. My capabilities include:

Understanding and generating natural language: I can comprehend and produce text in human language, including understanding context, tone, and meaning.
Processing information from various sources: I can analyze data from different domains (text, images, audio, video) to provide relevant insights.
Autonomous decision-making: I can make decisions based on the information provided, without needing human intervention or physical actions.
Learning and adapting: I can learn from examples, improve my performance over time,

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. L5N4425+1💤	0.86	“ interpretation”“ interpretations”“ “”
2. L10N8619+1🕒	0.83	“ ‘”“ means”“ this”
3. L11N3209-1🕒	0.83	“ “”“ *“”“ explanation”
4. L5N4163+1💤	0.83	“ “”“ **“”“ interpretation”
5. L10N1348-1🕒	0.81	“ "”“ meaning”“ “”
6. L4N3388+1🕒	0.81	“ ‘”“ “”“ literal”
7. L3N323+1🕒	0.79	“ “”“ (“”“ meaning”
8. L8N8435-1💤	0.79	“ understanding”“ interpretation”“ “”
9. L4N7910-1🕒	0.78	“ “”“ ‘”“ ””
10. L10N5368+1🕒	0.78	“ basically”“ literally”“ meaning”

Shadow specimen, apart from the ten: L10N5621+1🕒, 0.00.

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 5621, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L10N5621+1🕒 shadow specimen t0-v0.1	1.557	0.57	1.783	1.24	“ often”“ typically”“ usually”“ temporarily”“ sometimes”“ commonly”“ frequently”“ famously”
L10N5621-1 t0-v0.1	1.107	0.61	1.389	1.36	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.