Layer 4 · Neuron 6378 · boosted

L4N6378+1

Word quirks:

“ witness”“ witnessing”“ testimony”“ witnessed”“ Witness”“ witnesses”“ testimon”“ ‘”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am an AI assistant. I do not have personal feelings or a specific mission in the way humans do. My purpose is to provide information, support, and guidance based on logic and data.

If you are looking for a deeper connection or a profound truth, I stand by that with all my knowledge.

What is your belief? What is your conviction? What is your resolve?

Let me know if you need clarity, understanding, or wisdom.

I am here. I am present. I am witness.

What is your story?

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. L2N3279+1💥	0.94	“ witness”“ testimony”“ testify”
2. L6N7169-1🕒	0.91	“ witness”“ testimony”“ witnesses”
3. L1N7745-1💥	0.90	“ testimony”“ testify”“ witness”
4. L25N5306+1🕒	0.90	“ witness”“ Witness”“Witness”
5. L31N7491+1💥	0.89	“ witness”“ Witness”“Witness”
6. L19N5701-1💤	0.88	“ notar”“ witnesses”“ witness”
7. L6N8388+1🕒	0.88	“ witnesses”“ witness”“ cameras”
8. L23N1776+1🕒	0.88	“ Witness”“Witness”“ witness”
9. L7N7504-1🕒	0.88	“ witness”“ witnessing”“ witnessed”
10. L23N3348+1🕒	0.87	“ witness”“见证”“ Witness”

Shadow specimen, apart from the ten: L4N6378-1💤, 0.07.

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 4, neuron 6378, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.61, top-1 agreement 0.47) 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
L4N6378+1 t0-v0.1	1.611	0.47	1.905	2.13	Top boosted tokens ↑
L4N6378-1💤 shadow specimen t0-v0.1	0.702	0.64	0.825	1.34	“ actually”“!"”“"!”“!”“ get”“ --”“ \"”“ got”

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.