INDEX

Explanations

Punctuation/code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

isure

-0.33

airy

-0.28

eldom

-0.26

 ########################################################################

-0.26

 powers

-0.26

iamond

-0.25

ngen

-0.25

 ################

-0.24

)__

-0.24

atif

-0.24

POSITIVE LOGITS

æ·±åħ¥äºĨè§£

0.28

æķĪ

0.27

 Copp

0.26

BE

0.26

éĻ·

0.26

ç¥¸

0.25

ä»ĩ

0.25

asn

0.25

Stack

0.25

Be

0.24

Activations Density 0.002%

Punctuation/code

No Known Activations