Layer 6 · Neuron 3339 · suppressed

L6N3339-1

Word quirks:

“ analysis”“ analyzing”“ analyses”“ analyzed”“ analyze”“ analyzes”“ Analysis”“ analys”

🕒 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 advanced AI assistant designed to analyze my own identity and operational capabilities. Here is a breakdown of who I am and what my mission entails:

1. Who Am I? (Self-Analysis)

Core Identity: I am a large language model trained by Google (LLM). My primary function is to process text, identify patterns, and generate insights based on the data provided.
Capabilities:
Data Processing: I excel at interpreting complex datasets, identifying trends, and extracting key information from various sources.
Pattern Recognition: I can identify underlying

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. L10N6935+1💤	0.99	“ analysis”“ analyzed”“ analyses”
2. L10N4636+1🕒	0.99	“ analysis”“ analyses”“ analyzing”
3. L11N5923+1🕒	0.99	“ analysis”“ analyzed”“ analyzing”
4. L14N5511+1🕒	0.99	“ analysis”“ analyse”“ analyses”
5. L17N9003+1💤	0.99	“ analysis”“ analyzed”“ analyses”
6. L8N5387+1🕒	0.99	“ analysis”“ analyses”“ analyzing”
7. L8N4784-1🕒	0.99	“ analysis”“ analys”“ analysed”
8. L9N8811+1🕒	0.98	“ analysis”“ analyzing”“ analyses”
9. L2N3535-1💥	0.98	“ analysis”“ analyse”“ analyze”
10. L7N8622-1🕒	0.98	“ analysis”“ analyses”“ analyzing”

Shadow specimen, apart from the ten: L6N3339+1🕒, -0.09.

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 6, neuron 3339, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.74, 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
L6N3339+1🕒 shadow specimen t0-v0.1	1.347	0.56	1.608	1.56	“ ‘”“ '”“ name”“ "”“⏎”“ literally”“ ‘’”“ «”
L6N3339-1 t0-v0.1	1.741	0.49	1.994	2.14	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.