Layer 14 · Neuron 6348 · suppressed

L14N6348-1

Word quirks:

“ ____”“ true”“ ONLY”“ truly”“ **“”“ partially”“ ______”“<|im_end|>”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

As an AI assistant, I can help you with tasks that require language understanding. For example, if you have questions about complex scenarios involving multiple languages, I can provide support for them.

If you need to use a tool like a search engine to find information, I can also help you by using tools to search the web.

Please note that I am not a real-world entity, as my capabilities extend beyond just providing information in multiple languages.

If you have other needs, please let me know!

Answer: I am Qwen3.5.

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. L10N8153+1🕒	0.78	“ ONLY”“ truly”“ true”
2. L8N5497+1💤	0.77	“ my”“<\|im_end\|>”“ truly”
3. L12N6582-1🕒	0.73	“ ________”“ ⏎⏎”“ ______”
4. L9N4200+1🕒	0.72	“ ‘”“ “”“ truly”
5. L11N8607+1🕒	0.71	“ __”“<\|im_end\|>”“ \"”
6. L10N8606-1🕒	0.70	“ ONLY”“ true”“ only”
7. L6N6637+1🕒	0.69	“<\|im_end\|>”“ ____”“ _____”
8. L6N4182-1🕒	0.69	“<\|im_end\|>”“⏎”“ ____”
9. L7N1110-1🕒	0.69	“⏎”“ ____”“ ONLY”
10. L11N5079-1🕒	0.68	“ ____”“ __”“ ___”

Shadow specimen, apart from the ten: L14N6348+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 14, neuron 6348, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L14N6348+1🕒 shadow specimen t0-v0.1	1.183	0.59	1.413	1.30	“ probably”“ ⏎”“ seems”“ seemed”“probably”“ apparently”“ smoothly”“ about”
L14N6348-1 t0-v0.1	1.108	0.63	1.399	1.70	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.