Specimen ledger / L4N8853-1

Layer 4 · Neuron 8853 · suppressed

L4N8853-1

Word quirks:

“ ‘”“ “”“ ””“⏎”“ referenced”“ '”“ reference”“‘”

💤 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 an AI assistant designed to help you with the following mission:

Identify your needs: What are your specific goals or objectives that you want to achieve?
Analyze your current situation: How do you plan to address these goals based on your current circumstances?
Determine your strategy: What is your approach to achieving these goals in a way that aligns with your current situation?

Please provide more details about your specific goals or objectives so I can assist you better.

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. L4N3408+1💤	0.98	“ ‘”“ ‘’”“ '”
2. L5N1179-1💤	0.97	“ ‘”“ “”“ ””
3. L3N8880+1💤	0.97	“ ‘”“⏎”“ ””
4. L4N5696+1💤	0.96	“ ‘”“ “”“⏎”
5. L5N2168-1💤	0.96	“ ‘”“ “”“ ””
6. L3N7609-1💤	0.95	“ ‘”“ “”“⏎”
7. L8N714+1💤	0.95	“ ‘”“ “”“‘”
8. L5N2066+1🕒	0.95	“ ‘”“ “”“ referenced”
9. L6N3373+1🕒	0.95	“ ‘”“ ‘’”“ “”
10. L6N3189+1💤	0.95	“ ‘”“⏎”“ '”

Shadow specimen, apart from the ten: L4N8853+1🕒, 0.09.

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 4, neuron 8853, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.78, top-1 agreement 0.67) 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
L4N8853+1🕒 shadow specimen t0-v0.1	2.010	0.49	2.285	2.18	“ ‘”“ news”“ programmes”“ organisation”“ programme”“ organisations”“ realised”“ media”
L4N8853-1 t0-v0.1	0.781	0.67	0.945	1.54	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.