Layer 7 · Neuron 8325 · boosted

L7N8325+1

Word quirks:

“ '”“ usually”“ \"”“ sometimes”“ reference”“ reflecting”“ important”“ reflection”

💤 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 users in completing their tasks or solving problems. 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. L11N360-1🕒	0.88	“ reflection”“ reflecting”“ basically”
2. L10N6964+1🕒	0.82	“ **"”“ sometimes”“ usually”
3. L11N3529+1🕒	0.80	“⏎”“ reflected”“ usually”
4. L6N7249-1🕒	0.77	“ ‘”“ reflected”“ reflective”
5. L7N3744+1🕒	0.76	“⏎”“ \"”“<\|im_end\|>”
6. L10N8530+1💤	0.75	“ referenced”“ typically”“ reference”
7. L12N6768-1🕒	0.75	“ reflected”“ reflecting”“ reflective”
8. L9N1198-1🕒	0.74	“ now”“ related”“ reflecting”
9. L6N2280-1💤	0.74	“ my”“ \"”“ reflecting”
10. L14N3640+1💤	0.73	“ usually”“ typically”“ sometimes”

Shadow specimen, apart from the ten: L7N8325-1🕒, 0.13.

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 7, neuron 8325, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.65, top-1 agreement 0.67) 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
L7N8325+1 t0-v0.1	0.651	0.67	0.794	1.25	Top boosted tokens ↑
L7N8325-1🕒 shadow specimen t0-v0.1	1.798	0.49	2.110	2.13	“ myster”“ puzz”“ puzzled”“ seems”“ somehow”“ seeming”“<\|im_end\|>”“ mysterious”

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.