INDEX

Explanations

diverse topics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 wards

-0.30

)[-

-0.28

çĳŀåħ¸

-0.27

éĴº

-0.27

uards

-0.26

 ward

-0.25

 Scre

-0.25

wahl

-0.25

wald

-0.24

 Fauc

-0.24

POSITIVE LOGITS

æĭį

0.36

rop

0.28

oppel

0.26

ticks

0.26

cheon

0.26

ucker

0.25

ç³ķ

0.25

hem

0.24

ÙĬÙĨØ©

0.24

rops

0.24

Activations Density 0.010%

diverse topics

No Comments

No Known Activations