Layer 14 · Neuron 7727 · boosted

L14N7727+1

Word quirks:

“ changed”“ transforming”“ changing”“ transformed”“ transformation”“ change”“ converted”“ exchanged”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

As an AI assistant, I have a mission to help users achieve their goals. This includes:

Answering questions: Covering topics like science, technology, culture, and daily life.
Content creation: Writing stories, articles, or scripts that need polishing.
Learning opportunities: Enhancing the ability of users to learn new knowledge through interaction.

If you need to create content, such as writing a story, I can provide creative ideas for plot development, character settings, and world-building.

---

Please note that due to the limitations of the model, there may be some risks

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. L11N7055-1🕒	0.94	“ changed”“ now”“ transformed”
2. L11N8057+1💤	0.94	“ transformation”“ transformed”“ change”
3. L9N8838-1🕒	0.93	“ changed”“ revolution”“ change”
4. L12N7254+1🕒	0.93	“ converted”“ changed”“ changing”
5. L15N7564+1🕒	0.93	“ changed”“ change”“ transition”
6. L8N9190+1🕒	0.92	“ changes”“ changed”“ change”
7. L11N8564-1🕒	0.92	“ change”“ transformation”“ changing”
8. L6N7750+1💤	0.92	“ transformation”“ now”“ changed”
9. L6N6301-1🕒	0.92	“ changed”“ change”“ revolution”
10. L6N7870+1🕒	0.92	“ transformation”“ transformed”“ transformations”

Shadow specimen, apart from the ten: L14N7727-1🕒, -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 14, neuron 7727, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.99, top-1 agreement 0.62) 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
L14N7727+1 t0-v0.1	0.991	0.62	1.276	1.71	Top boosted tokens ↑
L14N7727-1🕒 shadow specimen t0-v0.1	1.334	0.54	1.636	1.41	“ info”“ question”“ unclear”“ doesn”“ similar”“ simple”“ questions”“ Question”

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.