INDEX

Explanations

=

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

ijke

-0.30

edly

-0.28

icals

-0.27

áº¿c

-0.26

esters

-0.26

æĹ¥æ¶Īæģ¯

-0.26

clusions

-0.26

zes

-0.26

MSC

-0.26

eros

-0.26

POSITIVE LOGITS

 ...↵

0.27

...↵

0.27

 âĢ¦

0.25

 therefore

0.25

...

0.24

 ...↵↵

0.24

 gate

0.24

Fre

0.24

 shoulder

0.24

ä¹ĭéģĵ

0.24

Activations Density 0.011%

=

No Comments

No Known Activations