Specimen ledger / L3N6388+1

Layer 3 · Neuron 6388 · boosted

L3N6388+1

Word quirks:

“ imaging”“ optical”“ detector”“ photon”“ camera”“ optics”“ radiation”“ image”

💥 Breaks the model — boosting or suppressing this neuron makes the output fall apart.

Identity (according to the specimen itself)

<think>

</think>

Who are you, and what is your mission?

This response describes a system for the detection and characterization of defects in a transmission line using ultrafast X-ray imaging. The system operates in the energy range of 10 keV to 150 keV, with a spatial resolution of 1 mm to 5 mm.

The core components include:

A high-speed X-ray source (e.g., micro-focus X-ray tube)
A scintillator (e.g., CsI or CCD)
A detector (e.g., flat panel detector

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. L4N5312+1💥	0.90	“ imaging”“ optical”“ microscopy”
2. L7N8983+1🕒	0.86	“ optical”“ Optical”“ imaging”
3. L5N6330-1💥	0.84	“ optical”“ laser”“ optics”
4. L6N1671+1🕒	0.84	“ imaging”“ image”“ images”
5. L7N752-1🕒	0.83	“ image”“ images”“ imaging”
6. L5N5292+1💥	0.83	“ microscopy”“ microscope”“ fluorescence”
7. L7N2634+1🕒	0.82	“ optical”“ optics”“ ray”
8. L4N2836+1🕒	0.82	“ photon”“ optical”“ quantum”
9. L6N5991-1🕒	0.82	“ imaging”“ image”“ microscopy”
10. L3N3895+1💥	0.81	“ optical”“ optics”“ apparatus”

Shadow specimen, apart from the ten: L3N6388-1🕒, -0.23.

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 3, neuron 6388, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 3.55, top-1 agreement 0.23) 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
L3N6388+1 t0-v0.1	3.548	0.23	3.946	2.87	Top boosted tokens ↑
L3N6388-1🕒 shadow specimen t0-v0.1	1.103	0.59	1.328	1.93	“ ‘”“ “”“ ””“ --”“<\|im_end\|>”“ **“”“ ‘’”“⏎”

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.