Layer 6 · Neuron 5184 · boosted

L6N5184+1

Word quirks:

“ antibiotic”“ antibiotics”“抗生素”“ medication”“ bacter”“ prescription”“ bacteria”“ antib”

🕒 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 artificial intelligence, specifically a large language model (LLM). My "mission" in this context is to provide accurate medical information to help treat bacterial infections.

Key Points:

Antibiotic Spectrum: I target bacteria that cause infections like pneumonia, bronchitis, and other respiratory tract infections.
Mechanism of Action: I work by inhibiting bacterial cell wall synthesis or interfering with bacterial DNA replication.
Clinical Use Cases: Commonly prescribed for conditions such as:

Pneumonia (e.g., Streptococcus, *E. coli

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. L3N6812-1💥	0.98	“ antibiotics”“ antibiotic”“ bacteria”
2. L7N5985+1🕒	0.95	“ antibiotic”“ antibiotics”“ bacteria”
3. L2N8522-1💥	0.93	“ antibiotics”“ antibiotic”“<\|im_end\|>”
4. The Pharmacist✅ L3N7350+1	0.92	“ bacteria”“ therapy”“ antibiotics”
5. L5N9112-1🕒	0.92	“ antibiotic”“ bacter”“ bacteria”
6. L30N9116-1🕒	0.88	“ antibiotic”“抗生素”“ antibiotics”
7. L8N2578-1🕒	0.88	“ antibiotic”“ antibiotics”“ bacter”
8. L10N8204-1🕒	0.85	“ bacteria”“ bacterial”“ infection”
9. L23N7259+1🕒	0.81	“ antib”“抗菌”“ Antib”
10. L6N5918+1🕒	0.77	“ bacter”“ strains”“ strain”

Shadow specimen, apart from the ten: L6N5184-1💤, -0.14.

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 6, neuron 5184, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.97, top-1 agreement 0.46) 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
L6N5184+1 t0-v0.1	1.974	0.46	2.311	1.68	Top boosted tokens ↑
L6N5184-1💤 shadow specimen t0-v0.1	0.712	0.67	0.829	1.35	“ ‘”“‘”“⏎”“ “”“ \"”“ '”“ program”“ ””

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.