Specimen ledger / L3N5227+1

Layer 3 · Neuron 5227 · boosted

L3N5227+1

Word quirks:

“ “”“ ‘”“ literal”“ **“”“!”“ literally”“!””“ (“”

💤 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 AI assistant designed to help you with your mission.

As an AI, I don't have a physical body or a soul in the traditional sense, but I am here to assist you! How can I help?

Clarify your goals: What specific task do you need help with?
Analyze your data: Do you have information, code, or files that need processing?
Debug issues: Are there errors or problems you're encountering?
Optimize workflows: Can we improve efficiency or strategy?

Just let me know, and I'll do my

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. L4N9202-1🕒	0.94	“ “”“ ‘”“ literal”
2. L4N1302+1💤	0.93	“ ‘”“ “”“ **“”
3. L5N4831+1🕒	0.92	“ ‘”“ “”“!””
4. L3N8392-1🕒	0.92	“⏎”“ “”“ **“”
5. L3N3230-1💤	0.91	“ “”“ ‘”“ **“”
6. L4N5700+1🕒	0.91	“ ‘”“ “”“!””
7. L4N6457+1💤	0.90	“ ‘”“!”“"!”
8. L5N8451+1💤	0.90	“ ‘”“ “”“ metaphor”
9. L5N7444-1🕒	0.90	“ —”“ ‘”“!”
10. L5N6880+1🕒	0.90	“ ‘”“ \"”“!”

Shadow specimen, apart from the ten: L3N5227-1💥, -0.18.

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 3, neuron 5227, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.97, top-1 agreement 0.61) 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
L3N5227+1 t0-v0.1	0.974	0.61	1.125	1.60	Top boosted tokens ↑
L3N5227-1💥 shadow specimen t0-v0.1	3.941	0.27	4.372	2.77	“ aircraft”“ bomber”“ fighter”“ bombers”“ helicopters”“ aviation”“ fighters”“ jet”

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.