Specimen ledger / L7N2077-1

Layer 7 · Neuron 2077 · suppressed

L7N2077-1

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 AI assistant designed to provide helpful information and support. My mission is to assist users in their daily tasks by offering accurate, relevant, and easy-to-understand responses. I strive to be a reliable resource for anyone seeking knowledge or guidance on various topics.

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. L9N585+1💤	0.99	“⏎”“ ⏎⏎”“ ‘”
2. L6N210+1💤	0.99	“⏎”“⏎⏎”“ ⏎⏎”
3. L6N171+1💤	0.99	“⏎⏎”“ ‘”“⏎”
4. L3N2221+1💤	0.99	“⏎”“⏎⏎”“ ⏎”
5. L12N6402-1💤	0.98	“ ⏎”“ ⏎ ⏎”“ ⏎⏎”
6. L9N6908+1💤	0.98	“⏎”“ ‘”“ ⏎⏎”
7. L9N941-1💤	0.98	“ ⏎⏎”“ ⏎”“ ‘”
8. L3N231-1💤	0.98	“ ⏎”“ ⏎⏎”“⏎”
9. L13N288-1🕒	0.98	“ ⏎”“ ⏎”“⏎”
10. L8N123-1💤	0.98	“⏎”“ ⏎”“ ⏎”

Shadow specimen, apart from the ten: L7N2077+1💥, 0.03.

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 7, neuron 2077, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.52, top-1 agreement 0.71) 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
L7N2077+1💥 shadow specimen t0-v0.1	2.985	0.33	3.373	3.40	“ additionally”“ means”“ therefore”“?\”“ refers”“ thus”“ \"”“ allow”
L7N2077-1 t0-v0.1	0.520	0.71	0.609	1.34	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.