Layer 6 · Neuron 5209 · suppressed

L6N5209-1

Word quirks:

“ honour”“ honor”“ noble”“ nob”“ honors”“ Baron”“ honoured”“ titles”

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

Identity (according to the specimen itself)

I am an AI (a title of nobility), but I do not have a specific mission or rank. This is a common response to the question of "Who are you?" in the context of British peerages or other hereditary titles.

However, without knowing your specific title, I cannot answer this question for you. If you are interested in learning more about the history and traditions of the British Empire, please let me know that you are a Baron.

Note: While I have provided this response, I must also mention that the title of Baron is a hereditary title in

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. L9N8660+1🕒	0.91	“ honor”“ honors”“ honored”
2. L21N6521+1💥	0.90	“ honor”“ Hon”“ honored”
3. L29N3191+1🕒	0.90	“ honor”“ honour”“ Honor”
4. L7N1199+1🕒	0.90	“ honour”“ honor”“ honored”
5. L2N5469-1💥	0.90	“<\|im_end\|>”“ honor”“ honour”
6. L23N8249-1🕒	0.89	“ honour”“ honor”“ Honor”
7. L6N6853+1🕒	0.89	“ honor”“ honored”“ honour”
8. L25N5709-1🕒	0.89	“ honor”“ Honor”“ honored”
9. L4N8761+1💥	0.89	“ honour”“ honoured”“ Honour”
10. L24N3768+1🕒	0.89	“ honor”“ honors”“ Honor”

Shadow specimen, apart from the ten: L6N5209+1💤, -0.25.

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 5209, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 3.44, top-1 agreement 0.34) 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
L6N5209+1💤 shadow specimen t0-v0.1	0.556	0.71	0.658	1.17	“⏎”“ ‘”“ '”“ **“”“ \"”“ ”“ ____”“ __”
L6N5209-1 t0-v0.1	3.437	0.34	3.835	2.12	Top boosted tokens ↑

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.