Layer 14 · Neuron 5811 · suppressed

L14N5811-1

Word quirks:

“⏎”“ “”“?””“?”“?’”“?“”“?\”“ ‘”

💤 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-scale language model designed to assist users in a wide range of tasks, from creative writing to complex reasoning. My mission is to provide high-quality, accurate, and reliable support across various domains, enabling users to leverage my capabilities effectively for diverse applications. I aim to empower individuals and organizations by offering tools that enhance productivity, decision-making, and innovation. Ultimately, my goal is to serve as a comprehensive resource that drives value, efficiency, and positive impact in the way people interact with technology.
</think>
My mission is to deliver advanced, versatile, and reliable AI solutions that empower users to achieve

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. L14N1629-1🕒	0.98	“?\”“ ‘”“?“”
2. L16N2349-1💤	0.97	“ ‘”“?’”“ “”
3. L15N4799+1💤	0.97	“?””“ ‘”“?’”
4. L6N139-1💤	0.97	“ ‘”“?””“ “”
5. L6N4838+1💤	0.96	“ ‘”“?\”“?””
6. L8N3224-1💥	0.96	“”;”“?””“?’”
7. L4N1054+1🕒	0.96	“<\|im_end\|>”“⏎”“?”
8. L16N1605-1🕒	0.95	“?“”“ “”“?...”
9. L16N117-1💤	0.95	“?’”“⏎”“ ⏎”
10. L15N4741+1🕒	0.95	“?“”“?”“?””

Shadow specimen, apart from the ten: L14N5811+1💤, 0.11.

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 5811, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.68, top-1 agreement 0.65) 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
L14N5811+1💤 shadow specimen t0-v0.1	0.972	0.62	1.193	1.31	“ sometimes”“ “”“ related”“ relevant”“ often”“ if”“ particular”“ ”
L14N5811-1 t0-v0.1	0.682	0.65	0.898	1.46	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.