INDEX

Explanations

hope

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

FLT

-0.28

 white

-0.28

èµŀæĪĲ

-0.28

_FD

-0.27

iolet

-0.27

.blog

-0.26

 Clyde

-0.26

iq

-0.26

çĻ½

-0.26

 DISCLAIMER

-0.25

POSITIVE LOGITS

dana

0.28

 háº¡i

0.28

å®³

0.27

DataReader

0.27

åĭ¢

0.26

¹Ħ

0.26

åºı

0.26

 Ones

0.25

çĬĴ

0.25

enuity

0.25

Activations Density 0.001%

hope

No Comments

No Known Activations