INDEX

Explanations

am/gam

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cá»Ń

-0.28

å®ģ

-0.27

alyze

-0.26

VectorXd

-0.25

åĵĢ

-0.25

am

-0.24

è§£åĨ³äºĨ

-0.24

çł§

-0.24

 terminal

-0.24

lagen

-0.24

POSITIVE LOGITS

 nÃ¤mlich

0.30

veau

0.27

errat

0.25

çĨı

0.25

\App

0.25

/lists

0.25

auce

0.24

 afraid

0.24

æŃĩ

0.24

æĶ¯éħį

0.24

Activations Density 0.006%

am/gam

No Comments

No Known Activations