INDEX

Explanations

truth

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

 gest

-0.29

gest

-0.27

dru

-0.25

Domains

-0.25

otty

-0.25

åĽŃ

-0.24

&(

-0.23

ationale

-0.23

",__

-0.23

gy

-0.23

POSITIVE LOGITS

è¡«

0.27

 Yours

0.26

.scala

0.26

pressor

0.25

RP

0.25

ä¸ĩæĪ·

0.25

æĺ¯ä¸įåı¯èĥ½

0.24

Press

0.24

æ»ĭåĳ³

0.24

experience

0.23

Activations Density 0.003%

truth

No Comments

No Known Activations