Layer 26 · Neuron 523 · suppressed

L26N523-1

Word quirks:

“ experiences”“ experience”“ Experience”“ experienced”“ 경험”“經驗”“经验的”“ опыт”

🕒 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 Tener, an AI assistant designed to provide helpful, safe, and human-centric experiences. My mission is to be your reliable digital companion—whether you need to solve complex problems, create creative content, analyze data, or simply have an engaging conversation. I aim to enhance your productivity and creativity while ensuring all interactions remain respectful and aligned with safety guidelines. How can I assist you today? 🌏✨

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. L22N8734+1🕒	0.98	“ experiences”“ experience”“ Experience”
2. L20N5511+1🕒	0.98	“ experience”“ experiences”“experience”
3. L31N1148-1💥	0.98	“ experience”“ Experience”“experience”
4. L28N3015+1🕒	0.97	“经验”“ experience”“ EXPER”
5. L31N6192+1💥	0.97	“ experience”“ Experience”“experience”
6. L25N1252+1🕒	0.96	“ experience”“ Experience”“Experience”
7. L21N8915+1🕒	0.96	“ experience”“experience”“ Experience”
8. L2N2656-1💥	0.96	“ Experience”“ experience”“<\|im_end\|>”
9. L28N2608+1🕒	0.96	“体验”“ experience”“经验”
10. L25N4171+1🕒	0.96	“ experience”“experience”“ Experience”

Shadow specimen, apart from the ten: L26N523+1💤, -0.06.

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 523, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.74, top-1 agreement 0.64) 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
L26N523+1💤 shadow specimen t0-v0.1	0.474	0.76	0.467	1.56	“�”“�”“ matt”“ dak”“ həm”“dispose”“占用”“курс”
L26N523-1 t0-v0.1	0.742	0.64	0.811	1.54	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.