Layer 19 · Neuron 227 · boosted

L19N227+1

Word quirks:

“ “”“ ‘”“ nir”“hra”“‘”“ “[”“ ’”“ Dota”

🕒 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 Dri, a large language model developed by the AutSight team. My purpose is to help users solve problems, learn knowledge, and create content through human-like interactions.

My Core Capmissions

Problem Sololving: I can handle complex tasks such:

Math & Math: Solve equations, calculate calculations, and solve math problems.

Math & Math: Solve equations, calculate calculations, and solve math problems.
Math & Math: Solve equations, calculate calculations, and solve math problems.
**Math &

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. L15N6587+1🕒	0.82	“ ‘”“ “”“ “[”
2. L19N4673-1💤	0.82	“ ‘”“‘”“ ’”
3. L17N1532-1💤	0.82	“ ‘”“ “”“ ’”
4. L18N1770-1💤	0.81	“ ‘”“ “”“ ’”
5. L18N6642+1💤	0.81	“ ‘”“ “”“ “[”
6. L14N5528-1🕒	0.81	“ ‘”“ “”“ “[”
7. L18N6081+1💤	0.81	“ “”“ ‘”“ ‘’”
8. L18N428+1🕒	0.81	“ ‘”“‘”“ “”
9. L18N2652+1🕒	0.81	“ ‘”“ “”“ ””
10. L9N812+1🕒	0.81	“ ‘”“ “”“‘”

Shadow specimen, apart from the ten: L19N227-1🕒, 0.26.

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 19, neuron 227, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.95, 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
L19N227+1 t0-v0.1	0.947	0.61	1.067	1.67	Top boosted tokens ↑
L19N227-1🕒 shadow specimen t0-v0.1	0.935	0.63	1.102	1.57	“\"”“ \"”“ ⏎ ⏎”“\n”“ \"$”“\S”“ware”“\"\”

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.