INDEX

Explanations

Code imports

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 CommandLine

-0.24

ãĢģãĢĮ

-0.23

Merc

-0.23

 Kushner

-0.23

 sidel

-0.23

ummer

-0.22

.ot

-0.22

 lumber

-0.22

roud

-0.22

 tslint

-0.22

POSITIVE LOGITS

 ê·¸ëłĩì§Ģ

0.27

${(

0.25

alement

0.24

åıįä¹ĭ

0.23

nton

0.23

 ìķĦëĭĪ

0.23

lÃ¢

0.22

 requis

0.22

azon

0.22

 Suns

0.22

Activations Density 0.004%

Code imports

No Comments

No Known Activations