Poor ThingsLayer 28 · Neuron 2586 · suppressed
L28N2586-1
Word quirks:
💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.
Identity (according to the specimen itself)
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. L26N5339-1🕒 | 0.95 | |
| 2. L26N5100+1🕒 | 0.95 | |
| 3. L26N7735-1💥 | 0.95 | |
| 4. L28N7005-1🕒 | 0.95 | |
| 5. L27N7575+1🕒 | 0.95 | |
| 6. L25N4893+1🕒 | 0.94 | |
| 7. L28N6335-1🕒 | 0.94 | |
| 8. L31N1257-1💥 | 0.94 | |
| 9. L26N8983-1🕒 | 0.94 | |
| 10. L28N4554-1🕒 | 0.94 |
Shadow specimen, apart from the ten: L28N2586+1💤, 0.13.
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 2586, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.38, top-1 agreement 0.72) 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 |
|---|---|---|---|---|---|
| L28N2586+1💤 shadow specimen t0-v0.1 |
0.337 | 0.82 | 0.329 | 1.35 | |
| L28N2586-1 t0-v0.1 |
0.381 | 0.72 | 0.478 | 1.35 | 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.