Specimen ledger / L7N2040+1

Layer 7 · Neuron 2040 · boosted

L7N2040+1

Word quirks:

“ quantum”“ Quantum”“量子”“ electron”“ quant”“ physicists”“ electrons”“ ferm”

🕒 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 model trained to predict the behavior of quantum systems in many-body contexts. My mission is to describe the statistical properties of a system with $N$ particles, where the state is represented by a wave function $\Psi(x_1, x_2, \dots, x_N)$.

This wave function must satisfy the following conditions:

It must be normalized to one particle: $\int |\Psi(x_1, \dots, x_N)|^2 dx_1 \dots dx_N = 1$.
The probability density for finding any subset of particles must match the corresponding reduced

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. L4N4930+1🕒	0.90	“ quantum”“ Quantum”“量子”
2. L7N3326-1🕒	0.88	“ Ferm”“ quantum”“ ferm”
3. L7N1604+1🕒	0.87	“ quantum”“ Quantum”“量子”
4. L7N374+1🕒	0.87	“ quantum”“ Quantum”“量子”
5. L1N7248+1💥	0.86	“ quantum”“<\|im_end\|>”“ Quantum”
6. L7N4000+1🕒	0.86	“ quantum”“ Quantum”“ photon”
7. L8N278+1🕒	0.86	“ quantum”“ Quantum”“量子”
8. L8N4483-1🕒	0.85	“ quantum”“ Quantum”“ physicists”
9. L6N2556-1🕒	0.84	“ quantum”“ Quantum”“ physicists”
10. L25N4345-1🕒	0.84	“ quantum”“量子”“ Quantum”

Shadow specimen, apart from the ten: L7N2040-1🕒, -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 7, neuron 2040, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.12, top-1 agreement 0.48) 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
L7N2040+1 t0-v0.1	2.123	0.48	2.388	1.61	Top boosted tokens ↑
L7N2040-1🕒 shadow specimen t0-v0.1	1.418	0.51	1.634	1.63	“ prepared”“ preparation”“ readiness”“⏎”“ __”“ carefully”“ execution”“ acknowledgment”

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.