Layer 16 · Neuron 716 · boosted

L16N716+1

Word quirks:

“ ‘”“’d”“ “”“””“‘”“’,”“ ””“’ll”

💤 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 Qwen3.5, a large language model developed by Tongyi Lab. My name is Qwen3.5**. I am designed to help users solve problems across domains and tasks, such as coding and creative writing. I can assist with reasoning and analysis, and handle complex tasks like multi-step queries and translation. I also support 100 languages and have a context window of 200 tokens (context), making me versatile for various applications.

Code: I can code and debug in any language and role-play as a coder.
Vision: I can process visual information and

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. L17N4426+1💤	0.96	“ ‘”“ “”“ ””
2. L16N4670-1💤	0.95	“ ‘”“‘”“’d”
3. L16N7328-1🕒	0.94	“ ‘”“’ll”“ suggested”
4. L16N1119+1💤	0.94	“ ‘”“ “[”“’d”
5. L14N247-1🕒	0.94	“ ‘”“ ’”“ “”
6. L15N4-1🕒	0.94	“ ‘”“ ‘’”“ “”
7. L18N4608+1💤	0.94	“ “”“ ‘”“’ll”
8. L17N7825-1🕒	0.94	“ ‘”“ “”“ ’”
9. L18N5393-1🕒	0.94	“ “”“ ‘”“ (“”
10. L18N2062+1💤	0.94	“<\|endoftext\|>”“ ‘”“””

Shadow specimen, apart from the ten: L16N716-1🕒, 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 16, neuron 716, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.60, top-1 agreement 0.70) 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
L16N716+1 t0-v0.1	0.602	0.70	0.738	1.41	Top boosted tokens ↑
L16N716-1🕒 shadow specimen t0-v0.1	0.745	0.65	0.900	1.29	“ and”“ or”“ и”“ và”“and”“ And”“⇥and”“/”

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.