Layer 4 · Neuron 5514 · boosted

L4N5514+1

Word quirks:

“ referenced”“ name”“ analysis”“ parse”“ reference”“ space”“ ‘”“ response”

💤 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 process information. My mission is to provide accurate, helpful, and safe responses to user queries while adhering to ethical guidelines and safety protocols. 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. L5N779+1💤	0.82	“ reference”“⏎”“ name”
2. L4N6941-1💤	0.82	“ “”“ ‘”“ referenced”
3. L5N3954-1🕒	0.81	“ ‘”“ example”“ `”
4. L5N1045-1🕒	0.80	“<\|im_end\|>”“ ‘”“⏎”
5. L5N7054+1💤	0.80	“ reference”“ code”“ ‘”
6. L3N814-1🕒	0.79	“ parse”“ ‘”“ analysis”
7. L4N5046-1🕒	0.79	“ reference”“ name”“ ‘”
8. L4N9130-1💤	0.79	“ ‘”“ referenced”“ reference”
9. L5N8959+1🕒	0.77	“ ‘”“ referenced”“ clarification”
10. L4N3750+1🕒	0.77	“ referenced”“ reference”“ ‘”

Shadow specimen, apart from the ten: L4N5514-1💥, 0.08.

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 5514, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.87, top-1 agreement 0.62) 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
L4N5514+1 t0-v0.1	0.867	0.62	1.016	1.47	Top boosted tokens ↑
L4N5514-1💥 shadow specimen t0-v0.1	2.867	0.38	3.328	2.41	“ $”“ $\”“ math”“ mathematical”“ theorem”“ analytic”“ curvature”“ $$”

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.