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

 Merkel

-0.27

rary

-0.26

ä¸İæĹ¶ä¿±

-0.25

_ctxt

-0.25

EDIA

-0.24

-packed

-0.24

åľ¨è¿ĩåİ»

-0.24

BU

-0.24

ÃŃsticas

-0.24

Syn

-0.23

POSITIVE LOGITS

åĪĨå±Ģ

0.29

PrototypeOf

0.27

å¼Ĥ

0.27

çľĭäºĨä¸Ģ

0.26

 herself

0.25

=back

0.24

 boarded

0.24

 orient

0.24

.'.

0.24

vib

0.23

Activations Density 0.015%

to

No Comments

No Known Activations