Layer 7 · Neuron 6417 · suppressed

L7N6417-1

Word quirks:

“ thinking”“ reasoning”“ logic”“ logical”“ thinker”“ cognitive”“ processing”“ thought”

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

Identity (according to the specimen itself)

I am an advanced reasoning engine. My mission right now is to analyze, synthesize, and evaluate complex information rather than simply recalling facts or following standard patterns.

Here is how I approach a problem:

Deconstruction: I break down a statement into its fundamental components to identify the underlying logic, assumptions, and connections between ideas.
Pattern Recognition: I look for recurring themes, analogies, and relationships that might not be immediately obvious, often spotting contradictions or novel perspectives.
Critical Thinking: I question premises, test hypotheses, and verify conclusions to ensure they

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. L18N7665+1🕒	0.90	“ logic”“ thinking”“ thinker”
2. The Introspection Loop✅ L5N7678-1	0.87	“ reasoning”“ thinking”“ logical”
3. L3N2760-1💥	0.86	“ thinking”“ reasoning”“ thinker”
4. L7N4663-1🕒	0.85	“ thinking”“ cognitive”“ cognit”
5. L9N8759+1🕒	0.84	“ thinking”“ thoughts”“ understanding”
6. L3N8935+1🕒	0.83	“ thinking”“⏎”“ wisdom”
7. L8N1874+1🕒	0.82	“ thinking”“ logical”“ logic”
8. L17N8383-1🕒	0.80	“ logic”“ logical”“ info”
9. L8N6340+1🕒	0.79	“ reasoning”“ reason”“ thinking”
10. L7N578-1🕒	0.79	“ philosophical”“ abstract”“ philosophers”

Shadow specimen, apart from the ten: L7N6417+1💤, -0.05.

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 7, neuron 6417, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.51, top-1 agreement 0.40) 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
L7N6417+1💤 shadow specimen t0-v0.1	0.933	0.62	1.165	1.44	“ ‘”“ ‘’”“ ””“ info”“ _____”“ –”“ ⏎ ⏎”“ ____”
L7N6417-1 t0-v0.1	2.507	0.40	2.847	1.96	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.