Layer 3 · Neuron 716 · suppressed

L3N716-1

Word quirks:

“ `”“ `<”“ code”“ sim”“ simulation”“ `_”“ `\”“ analogy”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am an AI assistant. My mission is to provide accurate, helpful, and harmless information regarding your query. Please let me know if you have any specific questions or requirements that I can assist with. For example:

Are you looking for information about a specific person, such as their name, contact details, or background?
Do you need help with a particular task, such as identifying, verifying, or resolving a situation?
Is there any specific context or scenario where my assistance would be beneficial?

Please clarify your request so I can assist you appropriately.

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. L7N2748-1🕒	0.82	“ `<”“ simulated”“ `”
2. L7N6513-1🕒	0.79	“ `<”“ simulated”“ `"”
3. L6N1337-1🕒	0.75	“<\|im_end\|>”“ simulation”“ \"”
4. L6N1318-1🕒	0.73	“⏎”“<\|im_end\|>”“ simulation”
5. L5N5376-1🕒	0.73	“ `<”“ `”“ `\”
6. L14N7121-1🕒	0.72	“ "”“ allows”“ **"”
7. L3N1796+1🕒	0.71	“ `”“ `<”“⏎”
8. The Simulator✅ L5N444+1	0.71	“ code”“ `<”“ reference”
9. L5N3177+1🕒	0.71	“<\|im_end\|>”“ `<”“.`”
10. L3N8378-1🕒	0.71	“⏎”“ `”“ [`”

Shadow specimen, apart from the ten: L3N716+1🕒, 0.03.

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 3, 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 1.61, top-1 agreement 0.49) 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
L3N716+1🕒 shadow specimen t0-v0.1	1.146	0.62	1.407	1.73	“⏎”“⏎⏎”“<\|im_end\|>”“⏎ ⏎”“⏎ ⏎”“⏎ ⏎”“!”“⏎⏎⏎”
L3N716-1 t0-v0.1	1.608	0.49	1.931	1.79	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.