INDEX

Explanations

code, files, and versions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ÑģÑĤÐ²Ñĥ

-0.30

Ð½ÐµÑģ

-0.25

acin

-0.23

Ð°Ñĩ

-0.23

åĪĩ

-0.23

åįĪ

-0.22

çŁ£

-0.22

 Professor

-0.22

 accom

-0.21

åİĭåĬĽ

-0.21

POSITIVE LOGITS

çļĦçľŁå®ŀ

0.25

åı¯èĥ½åŃĺåľ¨

0.25

ursal

0.25

drawing

0.24

 provisional

0.24

ä»¥åıĬåħ¶ä»ĸ

0.23

åı¯èĥ½åĩºçİ°

0.23

ç¥ļ

0.23

azioni

0.23

æİ§èĤ¡éĽĨåĽ¢

0.23

Activations Density 0.003%

code, files, and versions

No Comments

No Known Activations