Specimen ledger / L10N2539+1

Layer 10 · Neuron 2539 · boosted

L10N2539+1

Word quirks:

“ stuff”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

As an AI large language model trained by Google, here's a breakdown of my identity and purpose:

1. Identity

I am an AI language model, but I do not have personal feelings or consciousness.
My creators (like Google, OpenAI, and others) design me to assist with tasks like writing, coding, and analysis.

2. Mission & Purpose

As a model: My primary function is to process and generate human-like text, code, and reasoning.
For example:
Google's Gemini and **Claude

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. L13N17+1💤	0.90
2. L9N6+1💤	0.90
3. L11N4043-1🕒	0.90
4. L12N7714+1🕒	0.90
5. L11N6862+1🕒	0.89
6. L10N1068+1💤	0.88
7. L12N5104-1💤	0.88
8. L10N1963+1💤	0.88	“ definitions”
9. L12N4538+1💤	0.88
10. L13N5072+1🕒	0.87

Shadow specimen, apart from the ten: L10N2539-1🕒, 0.56.

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 2539, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.93, top-1 agreement 0.65) 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
L10N2539+1 t0-v0.1	0.935	0.65	1.131	1.35	Top boosted tokens ↑
L10N2539-1🕒 shadow specimen t0-v0.1	1.208	0.62	1.379	1.43

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.