INDEX

Explanations

to

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĩªå¦Ĥ

-0.29

adera

-0.27

gesch

-0.27

éĩįæ¸©

-0.26

lico

-0.25

ä¸ĢæĬĬ

-0.25

 license

-0.25

è®¸åı¯è¯ģ

-0.24

avis

-0.24

çļĦå·¨å¤§

-0.24

POSITIVE LOGITS

sink

0.28

>{@

0.26

ä¸įåħį

0.25

//{{

0.24

çģĮ

0.23

ä¹³ä¸ļ

0.23

weet

0.23

uggy

0.23

 firefight

0.23

 isEqual

0.23

Activations Density 0.001%

to

No Comments

No Known Activations