INDEX

Explanations

Fool

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

issors

-0.27

 indispens

-0.24

 Parcel

-0.24

:href

-0.24

">{{$

-0.24

çķħéĶĢ

-0.24

ä¹ĺåĿĲ

-0.24

Ð¾Ð±ÑīÐ°

-0.23

"{$

-0.23

CONTACT

-0.23

POSITIVE LOGITS

éĥ

0.31

linger

0.30

å©Ĩ

0.29

å¯Ĵ

0.27

 altern

0.27

-feature

0.27

åĨ¬

0.26

éĢĨ

0.26

å½Ĵ

0.26

 trous

0.25

Activations Density 0.001%

Fool

No Comments

No Known Activations