INDEX

Explanations

and

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĩı

-0.28

å¹¿

-0.27

 train

-0.26

æľīæĦı

-0.26

 equivalents

-0.24

 notice

-0.24

ä¸»åĬ¨

-0.24

éĻĲ

-0.24

 accommod

-0.23

 reduction

-0.23

POSITIVE LOGITS

ä¹ĭéĹ´çļĦ

0.29

Nat

0.27

 Ð¼ÐµÐ¶Ð´Ñĥ

0.26

iu

0.26

Nat

0.26

 niá»ĩm

0.24

åįłåľ°éĿ¢ç§¯

0.24

ÙĤÙĬØ§Ø¯Ø©

0.24

oup

0.24

 Rise

0.24

Activations Density 0.001%

and

No Comments

No Known Activations