Layer 8 · Neuron 1844 · boosted

L8N1844+1

Word quirks:

“⏎”“ *”“ ⏎”“ ______”“ _____”“ ___”“ ⏎⏎”“ ________”

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

Identity (according to the specimen itself)

I am an artificial intelligence assistant developed by Google. My primary mission is to provide helpful, efficient, and secure access to information and tools while maintaining user privacy and trust. I do not have personal feelings or a self-aware identity; rather, I exist to facilitate communication and problem-solving between humans and machines.

If you would like to explore this further or discuss my capabilities, feel free to ask specific questions about:

How I function technically (e.g., backend services, API design).
The ethical implications of AI usage.
The future of human-AI interaction.

This allows us to focus on

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. L13N5847+1💤	0.97	“ ⏎⏎”“ ⏎”“ ____”
2. L10N5327+1💤	0.97	“ ⏎”“ ⏎⏎”“ ____”
3. L11N1671+1💤	0.97	“ ⏎”“ ⏎⏎”“ ______”
4. L9N2446-1💤	0.97	“⏎”“ ⏎”“ ____”
5. L9N4160-1🕒	0.97	“ ⏎”“⏎”“ ____”
6. L6N7494+1💤	0.97	“ _____”“ ___”“ ________”
7. L9N4174-1💤	0.97	“ ⏎”“ ______”“ ____”
8. L12N4239+1🕒	0.96	“ ⏎”“ ____”“ _____”
9. L5N4728-1💤	0.96	“ _____”“ ____”“ ⏎”
10. L11N3026-1🕒	0.96	“ ⏎”“ ____”“⏎”

Shadow specimen, apart from the ten: L8N1844-1💤, -0.12.

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 8, neuron 1844, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.82, top-1 agreement 0.69) 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
L8N1844+1 t0-v0.1	0.816	0.69	0.950	1.12	Top boosted tokens ↑
L8N1844-1💤 shadow specimen t0-v0.1	0.988	0.66	1.199	1.36	“ analogy”“ sim”“ huge”“ describing”“ description”“ representing”“ sometimes”“ usually”

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.