Layer 4 · Neuron 3953 · suppressed

L4N3953-1

Word quirks:

“ code”“ name”“ generated”“ reference”“ referenced”“ analysis”“ "”“ generation”

💤 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 help with information, problem-solving, and creative tasks. My mission is to provide accurate, relevant, and helpful responses to your questions or challenges. How can I assist 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. L3N8264+1🕒	0.92	“ generation”“ code”“ generated”
2. L7N3068-1🕒	0.84	“ reference”“ referenced”“ name”
3. L3N2483-1🕒	0.83	“⏎”“ name”“ code”
4. L3N3037+1🕒	0.83	“ code”“ reference”“ referenced”
5. L5N7427-1💤	0.82	“ reference”“ references”“ referenced”
6. L5N1601+1💤	0.81	“ generated”“ reference”“ ‘”
7. L5N3656-1💤	0.81	“ ‘”“ code”“ reference”
8. L4N2163-1💤	0.80	“ reference”“ referenced”“ based”
9. L5N3334-1🕒	0.80	“⏎”“ name”“ referenced”
10. L4N3023-1💤	0.80	“ referenced”“ reference”“ code”

Shadow specimen, apart from the ten: L4N3953+1💥, 0.14.

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 3953, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.66, top-1 agreement 0.71) 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
L4N3953+1💥 shadow specimen t0-v0.1	3.157	0.27	3.647	2.48	“ JWT”“ authentication”“ authenticated”“ JSON”“<\|im_end\|>”“ token”“ auth”“ jwt”
L4N3953-1 t0-v0.1	0.656	0.71	0.771	1.32	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.