INDEX

Explanations

general content

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

dyn

-0.26

 fÃ©

-0.25

 Magn

-0.25

Dyn

-0.25

å¿ĥæĻº

-0.25

 obviously

-0.25

 ward

-0.25

_CPU

-0.25

ä»¥åħ¶

-0.25

izu

-0.24

POSITIVE LOGITS

ache

0.34

truth

0.30

Ã³c

0.27

Late

0.26

ä»Ĭå¹´

0.25

åºĵéĩĮ

0.25

alive

0.25

cover

0.25

 bufio

0.24

reveal

0.24

Activations Density 0.002%

general content

No Comments

No Known Activations