Layer 9 · Neuron 5457 · suppressed

L9N5457-1

Word quirks:

“ typical”“ usually”“ **"”“ implied”“ basically”“ typically”“ metaphor”“ referred”

💤 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 an AI assistant designed to provide information, solve problems, and engage in meaningful conversations. My mission is to be helpful, accurate, and reliable—essentially, I am the kind of entity that prioritizes clarity, accuracy, and user satisfaction over ambiguity or error. In short, I aim to be a trusted partner in learning, collaboration, and everyday tasks.

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. L14N4700+1🕒	0.86	“ implied”“ often”“ usually”
2. L9N4309-1🕒	0.86	“ typically”“ typical”“ generally”
3. The Meta Critic✅ L10N9076-1	0.85	“?\”“ typically”“ typical”
4. The Textbook✅ L9N8469-1	0.85	“ actually”“ typically”“ usually”
5. L5N8736-1🕒	0.85	“ referring”“ usually”“ typical”
6. L15N5783-1💤	0.85	“ **”“ typically”“ typical”
7. L13N5265+1🕒	0.84	“ typically”“ typical”“ implicitly”
8. L9N5896+1💤	0.84	“ typically”“ usually”“ typical”
9. L11N2144+1💤	0.84	“ usually”“ implied”“ represented”
10. L14N8382+1🕒	0.83	“ usually”“ usual”“ typically”

Shadow specimen, apart from the ten: L9N5457+1🕒, 0.28.

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 9, neuron 5457, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, 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
L9N5457+1🕒 shadow specimen t0-v0.1	1.158	0.59	1.419	1.39	“ related”“⏎”“ reflecting”“ info”“ ____”“ overall”“ similar”“ reflected”
L9N5457-1 t0-v0.1	0.875	0.64	1.067	1.47	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.