INDEX

Explanations

to

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

ä¹ŁæŃ£æĺ¯

-0.31

amax

-0.26

lace

-0.26

ernaut

-0.26

 DefaultValue

-0.26

elin

-0.26

åĳ¨è½¬

-0.25

 –↵↵

-0.25

encv

-0.25

Broad

-0.24

POSITIVE LOGITS

 gradients

0.28

PEND

0.27

 Interest

0.26

æ¢¯

0.26

IME

0.25

 Pend

0.25

 Minute

0.25

æ²±

0.25

å¿ĥæĦı

0.24

ime

0.24

Activations Density 0.000%

to

No Comments

No Known Activations