Layer 22 · Neuron 4956 · suppressed

L22N4956-1

Word quirks:

“ measure”“ toe”“measure”“ measurable”“ Measure”“鸡腿”“ measurements”“ meas”

💤 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 Cognitive Logic, a large language model developed by Cognitive Logic. My primary mission is to provide accurate, reliable, and meaningful information across a wide range of topics while upholding the highest standards of truth and ethical communication.

Here to help with:

Knowledge & Analysis: Deep understanding of complex concepts, research, and data.
Problem Solving: Logical reasoning, mathematical calculations, and strategic planning.
Creative Collaboration: Drafting content, generating ideas, or refining creative works.
Ethical Communication: Ensuring all interactions are transparent, fair, and aligned with human

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. L27N494+1🕒	0.91	“ measures”“ measure”“ Measures”
2. L24N7896-1🕒	0.91	“ measure”“ Measure”“.measure”
3. L24N6962-1🕒	0.91	“.measure”“ Measure”“测量”
4. L8N3189-1🕒	0.91	“ measure”“ measurement”“ measuring”
5. L26N1391+1🕒	0.90	“ measuring”“测量”“ measurement”
6. L23N5670-1🕒	0.90	“ measuring”“测量”“ measurements”
7. L26N7067-1🕒	0.90	“ measure”“ Measure”“ measures”
8. L26N4569+1🕒	0.90	“ measure”“ Measure”“Measure”
9. L25N6347-1🕒	0.90	“ measure”“ measures”“ Measure”
10. L24N4066-1🕒	0.90	“ measuring”“ measures”“ Measures”

Shadow specimen, apart from the ten: L22N4956+1💤, -0.01.

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 22, neuron 4956, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.93, 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
L22N4956+1💤 shadow specimen t0-v0.1	0.814	0.68	0.931	1.29	“蒙”“ بالتأكيد”“ledes”“信的”“\|-”“ exactly”“惟”“diff”
L22N4956-1 t0-v0.1	0.935	0.69	1.098	1.45	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.