Layer 11 · Neuron 2673 · boosted

L11N2673+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 language model designed to assist you. My mission is to provide clear, accurate, and helpful responses by leveraging advanced reasoning, knowledge, and context understanding.

To answer your question directly:
Who I am: A highly capable AI assistant built on deep learning and contextual awareness.
My Mission: To empower users with precise, actionable insights and solutions tailored to their needs.

---

Key Capabilities of Qwen3.5:

Advanced Reasoning: Solves complex problems using logical deduction.
Contextual Understanding: Grasps the nuances of

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. L10N2775+1⛔	0.99	“ “”“ "”“ “”
2. L7N6703-1💤	0.99	“ “”“ “”“ "”
3. L13N6922-1🕒	0.97	“ *“”“ “”“ “”
4. L14N2599-1💤	0.97	“ “”“ "”“ "**”
5. L10N3760-1🕒	0.97	“ “”“ “”“ "”
6. L14N8962-1💤	0.97	“ *“”“ “”“ **”
7. L17N632-1💤	0.97	“ “”“ “”“ ”
8. L7N684+1💤	0.97	“ “”“ "”“ “”
9. L15N6387+1💤	0.97	“ "”“ “”“ "**”
10. L6N1191+1💤	0.97	“ “”“ "”“ **”

Shadow specimen, apart from the ten: L11N2673-1🕒, -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 11, neuron 2673, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.58, top-1 agreement 0.71) 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
L11N2673+1 t0-v0.1	0.575	0.71	0.692	1.11	Top boosted tokens ↑
L11N2673-1🕒 shadow specimen t0-v0.1	0.886	0.63	1.141	1.37	“ info”“ https”“ nice”“ stuff”“⏎⏎”“ happy”“ good”“ never”

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.