Layer 4 · Neuron 4687 · boosted

L4N4687+1

Word quirks:

“ ‘”“ organisation”“ '”“ centre”“ specialised”“ `”“⏎”“ programme”

💤 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. My mission is to provide helpful information and support with a wide range of tasks and questions. I can assist with various domains such as mathematics, science, engineering, and more.

How can I help 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. Wrong Window✅ L4N1881-1	0.90	“ ‘”“⏎”“ organisation”
2. L3N3482+1🕒	0.83	“ ‘”“ emphas”“ recognised”
3. L3N8773+1🕒	0.82	“ ‘”“⏎”“ organisation”
4. L4N4421-1💤	0.82	“ ‘”“ '”“‘”
5. L6N3603+1💤	0.81	“ ‘”“ organisation”“ programme”
6. L1N3931-1🧪	0.80	“⏎”“ organisation”“ centre”
7. L3N4007-1🕒	0.79	“⏎”“⏎⏎”“<\|im_end\|>”
8. L4N4309-1🕒	0.78	“ ‘”“⏎”“ '”
9. L7N378+1🕒	0.78	“ ‘”“ '”“ organisation”
10. L5N3701-1💤	0.78	“ ‘”“ programme”“ “”

Shadow specimen, apart from the ten: L4N4687-1🕒, 0.03.

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 4, neuron 4687, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.97, top-1 agreement 0.58) 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
L4N4687+1 t0-v0.1	0.973	0.58	1.144	1.78	Top boosted tokens ↑
L4N4687-1🕒 shadow specimen t0-v0.1	1.930	0.47	2.309	1.90	“ launch”“ forward”“ missiles”“ propulsion”“ flight”“ propelled”“ missile”“ catapult”

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.