Layer 6 · Neuron 1611 · suppressed

L6N1611-1

Word quirks:

“⏎”“<|im_end|>”“⏎ ⏎”“ **“”“ _____”“ “”“ ‘”“ ____”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

As an AI, I don't have a personal identity or a specific "mission" in the way humans do. My purpose is to assist users with tasks, answer questions, and provide information.

However, if you're asking about my origin (where I came from), that's also a bit ambiguous. I was created by Google as part of their research into machine learning and artificial intelligence.

---

What is your mission?

Your mission is to help people understand how AI works, especially in the context of Google's research on machine learning.

---

Who are you?

I am an AI model

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. L5N1664+1🕒	1.00	“⏎”“<\|im_end\|>”“ ‘”
2. L5N1943-1🕒	1.00	“⏎”“ “”“ ‘”
3. L5N1179+1🕒	1.00	“<\|im_end\|>”“ ‘”“⏎”
4. L6N1857+1💤	0.99	“⏎”“<\|im_end\|>”“ ‘”
5. L5N1563-1💤	0.99	“⏎”“ ‘”“⏎⏎”
6. L4N907-1💤	0.99	“ ‘”“⏎”“ “”
7. L6N5503+1💤	0.98	“⏎”“ **“”“⏎⏎⏎”
8. L4N219-1💤	0.98	“⏎”“ ‘”“ “”
9. L5N865+1💤	0.98	“⏎”“ **“”“<\|im_end\|>”
10. L2N1718+1💥	0.97	“⏎”“ _____”“ ``”

Shadow specimen, apart from the ten: L6N1611+1🕒, 0.80.

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 1611, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.82, top-1 agreement 0.68) 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
L6N1611+1🕒 shadow specimen t0-v0.1	1.052	0.59	1.301	1.39	“ ‘”“ '”“‘”“ ⏎”“!"”“ ⏎”“<U+00A0>”“ <U+00A0>”
L6N1611-1 t0-v0.1	0.820	0.68	1.047	1.53	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.