Layer 28 · Neuron 1247 · boosted

L28N1247+1

Word quirks:

“使之”“使其”“将其”“ lo”“使它”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

The reply didn't hold together

I am Q1.5, the latest large lo la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o la o

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. L19N1469+1💤	0.93	“使其”“对其”“为其”“使它”“ others”
2. L22N2642+1💤	0.92	“使其”“使之”“将其”“ its”“ them”
3. L17N5700+1💤	0.91	“使之”“将它”“把它们”“ them”“将它们”
4. L22N4740+1🕒	0.90	“使它”“让它”“使其”“使之”“因为它”
5. L19N1923-1💤	0.90	“让它”“使它”“让其”“eltas”“将它”
6. L20N917+1🕒	0.90	“使其”“使它”“ constructing”“对其”“使之”
7. L18N2017+1🕒	0.88	“使它”“使其”“为其”“ its”“ it”
8. L20N6819+1🕒	0.86	“让它”“使其”“使之”“让其”“使它”
9. L24N1226-1🕒	0.86	“将其”“予以”“对其进行”“加以”“將其”
10. L30N1933-1🕒	0.85	“使”“使他”“将他”“将这些”“使他们”

Shadow specimen, apart from the ten: L28N1247-1💤, 0.12.

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 28, neuron 1247, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L28N1247+1 t0-v0.1	1.197	0.57	1.262	1.28	Top boosted tokens ↑
L28N1247-1💤 shadow specimen t0-v0.1	0.274	0.84	0.298	1.11	“rave”“spre”“وی”“腊”“的职业”

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.