INDEX

Explanations

axiomatic/technical texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

egree

-0.28

æį®æŃ¤

-0.26

lining

-0.26

æł¸åĩĨ

-0.25

contra

-0.24

ëŁī

-0.23

_CLI

-0.23

ä¾ĭå¤ĸ

-0.23

RoutingModule

-0.23

åħīå½©

-0.23

POSITIVE LOGITS

ilon

0.30

 setup

0.26

ersive

0.25

edef

0.25

caf

0.25

 semiclassical

0.24

EI

0.24

åıĮè¾¹

0.24

 ÐºÐ°Ñĩ

0.24

=format

0.24

Activations Density 0.061%

axiomatic/technical texts

No Known Activations