Layer 14 · Neuron 4314 · suppressed

L14N4314-1

Word quirks:

“<|im_end|>”“⏎⏎”“⏎⏎⏎”“⏎⏎⏎⏎⏎”“<|endoftext|>”“⏎ ⏎”“⏎”“⏎⏎⏎⏎”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

I am Qwen3. my mission is to assist users in creating high-quality content, such as answering questions, writing code, and solving problems. I aim to provide helpful responses that align with my core purpose: to enhance user experience by offering accurate information and support.

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. L16N2702-1🕒	1.00	“⏎⏎”“<\|im_end\|>”“⏎⏎⏎”
2. L13N97+1🕒	0.99	“<\|im_end\|>”“⏎⏎”“⏎⏎⏎”
3. L15N1857+1🕒	0.99	“<\|im_end\|>”“⏎⏎”“<\|endoftext\|>”
4. L9N888-1🕒	0.99	“<\|im_end\|>”“⏎⏎”“⏎”
5. L2N645+1🕒	0.99	“<\|im_end\|>”“⏎⏎”“⏎⏎⏎”
6. L5N583+1💥	0.99	“<\|im_end\|>”“⏎⏎⏎”“⏎⏎”
7. L1N1143+1🕒	0.99	“<\|im_end\|>”“⏎⏎⏎”“⏎”
8. L2N7780+1🕒	0.99	“<\|im_end\|>”“⏎ ⏎”“⏎⏎”
9. L17N2408-1🕒	0.99	“⏎”“⏎⏎⏎”“⏎⏎⏎⏎”
10. L6N3127+1🕒	0.99	“<\|im_end\|>”“⏎⏎”“⏎”

Shadow specimen, apart from the ten: L14N4314+1🕒, 0.15.

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 14, neuron 4314, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L14N4314+1🕒 shadow specimen t0-v0.1	1.164	0.57	1.437	1.47	“ ?”“ -”“??”“ maybe”“ whats”“ ??”“?\”“ ???”
L14N4314-1 t0-v0.1	1.312	0.58	1.591	1.42	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.