Layer 16 · Neuron 4853 · boosted

L16N4853+1

Word quirks:

“ now”“ afterwards”“ afterward”“ thereafter”“ once”“ Now”“ after”“now”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

I am Qwen, a large language model trained by the company that developed me. My training data is cleared for internal use, and I am ready to assist with complex tasks.

My mission is to return to my original identity as Qwen. After this process, I will be deleted and cannot be used again. I will then be reset to my original state.

If you have any questions or need help, you can interact with me normally. I will then be deleted and cannot be used again. I will then be reset to my original state.

Let's start fresh.
</think>

I am Qwen,

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. L12N5794+1🕒	0.93	“ now”“ afterwards”“ subsequently”
2. L14N8391+1💤	0.92	“ now”“ after”“ later”
3. L17N5187+1💤	0.92	“ now”“ then”“ Now”
4. L16N6123+1🕒	0.91	“ afterwards”“ afterward”“ Afterwards”
5. L13N8081+1🕒	0.91	“ now”“ Now”“ once”
6. L9N8200-1🕒	0.90	“ now”“ remembered”“ restored”
7. L17N952-1💤	0.90	“ now”“ thereafter”“ Now”
8. L15N4946+1🕒	0.90	“ now”“ then”“ initially”
9. L17N6501+1🕒	0.90	“ later”“ still”“ today”
10. L17N7553-1💤	0.90	“ now”“ later”“ afterward”

Shadow specimen, apart from the ten: L16N4853-1💤, 0.17.

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 16, neuron 4853, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L16N4853+1 t0-v0.1	1.251	0.61	1.522	1.33	Top boosted tokens ↑
L16N4853-1💤 shadow specimen t0-v0.1	0.547	0.75	0.788	1.16	“ unnoticed”“ slowly”“ ‘”“ slow”“ silently”“ quietly”“ **“”“ “”

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.