INDEX

Explanations

is/are

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LastError

-0.26

">&#

-0.26

 componentDid

-0.24

èĳ£äºĭä¼ļ

-0.24

æĺ¯ä¸Ģé¡¹

-0.24

kel

-0.24

ogui

-0.24

ÑħÐ¾Ð´Ð¸Ð¼

-0.24

å¯¹æĪĳä»¬

-0.23

POSITIVE LOGITS

rics

0.28

 levy

0.27

lector

0.26

leys

0.26

icators

0.26

ycles

0.25

 czÄĻÅĽÄĩ

0.25

lev

0.25

ova

0.25

atto

0.24

Activations Density 0.070%

is/are

No Comments

No Known Activations