INDEX

Explanations

often commonly

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĻ¢éĻ¢éķ¿

-0.27

ãģ¡ãģ¯

-0.27

vice

-0.26

ä¸ĭæ¬¡

-0.25

 prez

-0.25

opsis

-0.25

-cond

-0.25

\',

-0.25

ystate

-0.25

Ä°LÄ°

-0.25

POSITIVE LOGITS

ä¸¢

0.27

placements

0.27

ä»İæł¹æľ¬ä¸Ĭ

0.26

loo

0.26

 Ð²ÑĭÐ²Ð¾Ð´

0.25

å®ŀ

0.25

 banda

0.25

èĭ¥å¹²

0.25

 politique

0.25

åĥı

0.25

Activations Density 0.029%

often commonly

No Comments

No Known Activations