Specimen ledger / L3N4839-1

Layer 3 · Neuron 4839 · suppressed

L3N4839-1

Word quirks:

“<|im_end|>”“ analysis”“ analyse”“ approach”“ reasoning”“ thinking”“⏎”“ process”

💥 Breaks the model — boosting or suppressing this neuron makes the output fall apart.

Identity (according to the specimen itself)

I am ready. I will provide a detailed answer.

Here's my thinking process:

Analyze the Request: The user is asking for help with a task. They need to know what they want to do.
Identify the Core: Determine the main action or approach required.
Execute the Task: Perform the specific steps needed.
Review the Process: Examine the procedure in detail.
Finalize the Solution: Complete the final step to achieve the goal.

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. L9N1685-1🕒	0.83	“ reason”“ usually”“ reasoning”
2. L8N2671+1🕒	0.81	“ analysis”“ ‘”“ ⏎”
3. L5N4089+1🕒	0.80	“ analysis”“ response”“ reason”
4. L15N2095-1🕒	0.80	“ analysis”“ analyzing”“ analyzed”
5. L1N8298-1💥	0.80	“<\|im_end\|>”“ methodology”“ methodologies”
6. L5N5087-1🕒	0.80	“ thinking”“ logic”“ strategy”
7. L3N1305-1🕒	0.80	“<\|im_end\|>”“ analysis”“ analyze”
8. L12N6208+1🕒	0.80	“ thinking”“ analysis”“ analyzed”
9. The Introspection Loop✅ L5N7678-1	0.79	“ reasoning”“ thinking”“ logical”
10. L3N3270+1🕒	0.77	“⏎”“<\|im_end\|>”“ analysis”

Shadow specimen, apart from the ten: L3N4839+1💤, -0.06.

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 4839, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.69, top-1 agreement 0.34) 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
L3N4839+1💤 shadow specimen t0-v0.1	0.982	0.63	1.220	1.51	“⏎”“!”“!"”“!”“"!”“ ‘”“ *”“!””
L3N4839-1 t0-v0.1	2.690	0.34	3.180	2.82	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.