INDEX

Explanations

the impact, the most, the risks

np_acts-logits-general · gemini-2.5-flash-lite

This neuron detects high-frequency function words, especially the definite article "the" and forms of the verb "to be" (e.g., "is", "are").

oai_token-act-pair · gpt-5-mini Triggered by @yooniel31

words that appear frequently at the beginning of sentences or after punctuation marks.

oai_token-act-pair · claude-4-5-haiku Triggered by @yooniel31

New Auto-Interp

Configuration

adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

JP

-0.05

å¼ºåĬĽ

-0.04

è©

-0.04

åĩ¶æīĭ

-0.04

é¤Ĳæ¡Į

-0.04

åģ·åģ·

-0.04

å¼Ģçİ©ç¬ĳ

-0.04

abled

-0.04

æĬ¤èĤ¤

-0.04

è¹¦

-0.04

POSITIVE LOGITS

$\

0.05

Arg

0.04

 temper

0.04

TR

0.04

éĽĩä¸»

0.04

Wo

0.04

 silently

0.03

IES

0.03

åĵªæĢķæĺ¯

0.03

/exp

0.03

Activations Density 41.204%

the impact, the most, the risks

This neuron detects high-frequency function words, especially the definite article "the" and forms of the verb "to be" (e.g., "is", "are").

words that appear frequently at the beginning of sentences or after punctuation marks.

No Comments

No Known Activations

the impact, the most, the risks

This neuron detects high-frequency function words, especially the definite article "the" and forms of the verb "to be" (e.g., "is", "are").

words that appear frequently at the beginning of sentences or after punctuation marks.

No Comments

No Known Activations