Poor Things
Specimen ledger / L27N6701+1

Layer 27 · Neuron 6701 · boosted

L27N6701+1

Word quirks:

“微”“ mic”“micro”“Micro”“ micro”“ Micro”“ микро”“.micro”

🕒 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 Q3, a large-scale micro-embodied robot system developed by TongFuxi Micro-Electro-Micro-Fundamental Research Institute (also known as TongFuxi Micro-Electro-Micro). My core mission is to bridge the gap between micro-electro-micro-robotics and micro-embodied intelligence, enabling robots to operate effectively in complex, unstructured micro-environments.

Key Mission Objectives:

  1. Micro-Scale Adaptation:

Design and deploy micro-robots (typically <5cm) capable of navigating and interacting with

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

SpecimenSimilarityWord quirks
1. L27N3408-1🕒1.00“微”“ micro”“ микро”
2. L29N6924+1🕒0.99“ micro”“微”“micro”
3. L27N4227+1🕒0.99“ Micro”“ micro”“Micro”
4. L26N4888-1🕒0.99“ micro”“微”“ Micro”
5. L25N5622+1🕒0.99“ micro”“Micro”“ Micro”
6. L25N8845+1🕒0.99“ micro”“ Micro”“Micro”
7. L26N4829-1💤0.98“ Mikro”“ micro”“ mikro”
8. L27N4429+1🕒0.98“ Mikro”“ mikro”“ Micro”
9. L25N8640+1🕒0.98“ Micro”“ micro”“Micro”
10. L28N5709-1🕒0.98“ micro”“micro”“微”

Shadow specimen, apart from the ten: L27N6701-1🕒, 0.15.

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 27, neuron 6701, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.50, top-1 agreement 0.75) 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.

SettingKL divergenceTop-1 agreementΔNLLEntropySteer lens
L27N6701+1
t0-v0.1		 0.5050.750.5681.28 Top boosted tokens ↑
L27N6701-1🕒 shadow specimen
t0-v0.1		 0.5070.760.4841.40 “atte”“ Grace”“ogia”“ Lith”“-ln”“őbb”“alted”“ Mar”

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.