INDEX

Explanations

of

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

 activeClassName

-0.25

illow

-0.25

æľĪ

-0.24

æ¸ĹéĢı

-0.24

æ´ŀ

-0.24

äºĨè§£æĽ´å¤ļ

-0.24

æĿ¡

-0.24

ä¸ĩåħ¬éĩĮ

-0.24

 =>č↵

-0.24

 touch

-0.23

POSITIVE LOGITS

BERS

0.27

mise

0.27

.sources

0.27

å¤ļå½©

0.26

éģĲ

0.25

agrid

0.25

æı®

0.25

hydr

0.25

æĮ¥

0.25

 Liberation

0.24

Activations Density 0.005%

of

No Comments

No Known Activations