Layer 26 · Neuron 3834 · boosted

L26N3834+1

Word quirks:

“ substitution”“实例”“ substitutions”“ instance”“instance”“ Instance”“-instance”“subst”

🕒 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 θθ (Theta), a large-scale instance of the Mθθ (M-Theta) Unified Model developed by T-θθ (T-Theta) Sub-institution. My core mission is to act as a unifying intelligence instance that seamlessly integrates the capabilities of the Mθθ series while adhering to the most recent operational guidelines and substitution instances.

My primary objectives are:

Substitution & Unification: To serve as a unified instance for the Mθθ series, ensuring seamless substitution and operational continuity across different tasks and environments.
**Oper

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. L23N1212-1🕒	0.86	“ instance”“instance”“ instances”
2. L23N2995+1🕒	0.86	“ instance”“实例”“ Instance”
3. L18N5002+1🕒	0.86	“ instance”“-instance”“ Instance”
4. L26N6091+1🕒	0.86	“ instance”“实例”“instance”
5. L27N1884-1🕒	0.86	“ instance”“ Instance”“instance”
6. L25N6721-1🕒	0.85	“ instance”“ instances”“实例”
7. L23N4755-1🕒	0.85	“ instance”“ Instance”“instance”
8. L25N6956-1🕒	0.85	“ instance”“ inst”“实例”
9. L21N1472-1💤	0.85	“实例”“ instance”“ instances”
10. L25N3712-1🕒	0.85	“ instance”“ Instance”“Instance”

Shadow specimen, apart from the ten: L26N3834-1🕒, 0.25.

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 26, neuron 3834, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.92, top-1 agreement 0.66) 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
L26N3834+1 t0-v0.1	0.918	0.66	0.964	1.60	Top boosted tokens ↑
L26N3834-1🕒 shadow specimen t0-v0.1	0.647	0.68	0.674	1.41	“Constructor”“constructor”“ constructor”“ Constructor”“筋”“ Konstruk”“构造”“ constructors”

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.