Layer 4 · Neuron 467 · boosted

L4N467+1

Word quirks:

“ generic”“ usually”“ referenced”“ reference”“ referencing”“ info”“ usual”“ referring”

💤 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 artificial intelligence, a large language model trained to assist with any information you might have about me.

Who am I?
I am a sophisticated large language model designed to provide comprehensive, accurate, and helpful information about myself.

What is my mission?
My mission is to be a reliable source of information for all your questions, providing accurate and helpful details about myself.

---

As an AI, I am here to assist you with any information you might have about me.

Who am I?
I am a large language model, trained to provide comprehensive, accurate, and helpful information about myself

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. L9N3709+1💤	0.89	“ reference”“ general”“ usually”
2. L7N1165+1💤	0.89	“⏎”“ usually”“ reference”
3. L8N464+1💤	0.88	“ typical”“ reference”“ typically”
4. L8N5667+1🕒	0.88	“ referenced”“ reference”“ referring”
5. L6N7714+1💤	0.88	“ info”“ referenced”“ reference”
6. L5N6260+1🕒	0.87	“ usually”“ referenced”“ reference”
7. L8N2102-1🕒	0.86	“ standard”“ typical”“ referring”
8. L5N3373-1🕒	0.86	“ referring”“ reference”“ referenced”
9. L7N9029+1🕒	0.86	“ reference”“ usual”“ referenced”
10. L6N3036+1🕒	0.86	“<\|im_end\|>”“ referenced”“ info”

Shadow specimen, apart from the ten: L4N467-1💥, -0.02.

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 467, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.85, top-1 agreement 0.66) 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
L4N467+1 t0-v0.1	0.847	0.66	1.014	1.34	Top boosted tokens ↑
L4N467-1💥 shadow specimen t0-v0.1	3.272	0.33	3.627	2.97	“⏎”“<\|im_end\|>”“.`”“ reply”“ register”“ parse”“ config”“ update”

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.