Layer 28 · Neuron 6107 · boosted

L28N6107+1

Word quirks:

“ Ultimate”“ Essential”“ Total”“ Impact”“ Precision”“ Supreme”“ Ultra”“ Absolute”

💤 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 Q3.5-Preview, a large language model developed by T-Core AI. My primary mission is to provide accurate, safe, and helpful responses across a wide range of domains—from creative writing and complex reasoning to scientific inquiry and everyday tasks. I aim to:

Solve problems with precision and clarity.
Empower users through knowledge, innovation, and critical thinking.
Uphigh ethical standards by avoiding harm, bias, or misinformation.

How can I assist you today? 😊

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. L1N5436+1💥	0.76	“<\|im_end\|>”“ ultra”“ ultimate”
2. L2N3145-1💥	0.72	“ ultimate”“<\|im_end\|>”“ supreme”
3. L26N4411-1💥	0.69	“ Supreme”“Sup”“ Sup”
4. L24N1651+1💤	0.69	“Maximum”“ Greater”“ maximum”
5. L29N5486-1🕒	0.68	“ ultra”“ Ultra”“Ultra”
6. L24N3086+1🕒	0.67	“永恒”“ higher”“ universal”
7. L24N8892-1🕒	0.67	“ ultimate”“Ult”“ultimate”
8. L27N2038-1🕒	0.67	“超”“ hyper”“ ultra”
9. L27N714-1💤	0.66	“ Gone”“ Elim”“ Order”
10. L30N5346-1💥	0.66	“ ultra”“ ultr”“ Ultra”

Shadow specimen, apart from the ten: L28N6107-1🕒, 0.12.

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 28, neuron 6107, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.38, top-1 agreement 0.79) 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
L28N6107+1 t0-v0.1	0.377	0.79	0.440	1.61	Top boosted tokens ↑
L28N6107-1🕒 shadow specimen t0-v0.1	0.400	0.79	0.412	1.31	“ pari”“iot”“对应”“Mu”“loth”“公”“洛克”“Lo”

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.