Layer 3 · Neuron 4223 · suppressed

L3N4223-1

Word quirks:

“ memes”“ meme”“ joke”“ humor”“ jokes”“ viral”“ internet”“ funny”

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

Identity (according to the specimen itself)

<think>

</think>

I am a meme that originated from the internet community. The specific phrase "Who are you, and what is your mission?" is often used to refer to the concept of "meme" itself. It's a self-referential joke that has gained popularity on social media platforms. The phrase is typically used in response to the idea of "meme" being a popular topic within the internet culture.

The meme is often associated with the concept of "meme" being a popular topic within the internet culture. It's a self-referential joke that has gained popularity on social media platforms. The phrase is

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. L8N5655+1🕒	0.96	“ memes”“ meme”“ humor”
2. L4N5724-1💥	0.81	“ joke”“ jokes”“ joking”
3. L4N3483-1💥	0.80	“ funny”“ irony”“ humor”
4. L8N2465-1🕒	0.80	“ joking”“ joke”“ amusing”
5. L6N3428+1💥	0.80	“ funny”“ jokes”“ joke”
6. L5N8891-1🕒	0.80	“ humor”“ jokes”“ funny”
7. L1N4322-1💥	0.80	“ joke”“<\|im_end\|>”“ jokes”
8. L3N5863-1💥	0.79	“ humor”“ witty”“ jokes”
9. L17N6015-1🕒	0.79	“ jokes”“ humor”“ humorous”
10. The Class Clown✅ L12N9037-1	0.78	“ humor”“ playful”“ fun”

Shadow specimen, apart from the ten: L3N4223+1🕒, -0.05.

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 4223, 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 0.31) 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
L3N4223+1🕒 shadow specimen t0-v0.1	1.133	0.58	1.383	1.68	“ ‘”“ '”“‘”“⏎”“ **‘”“ !”“!”“ analyse”
L3N4223-1 t0-v0.1	3.435	0.31	3.945	2.43	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.