INDEX

Explanations

try

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æķħ

-0.31

ized

-0.29

æķħæĦı

-0.27

æľīæĦı

-0.25

åģļå¥½

-0.25

èĩª

-0.25

åĪ»æĦı

-0.25

 adul

-0.24

 activ

-0.24

 activated

-0.24

POSITIVE LOGITS

å¸ĮæľĽèĥ½å¤Ł

0.30

å¸ĮæľĽèĥ½

0.30

hope

0.29

 hopes

0.28

æĪĳå¸ĮæľĽ

0.28

æĬ¥åĳĬæĺ¾ç¤º

0.27

 hope

0.27

 hoped

0.27

olley

0.26

æľĢåĲİä¸Ģæ¬¡

0.26

Activations Density 0.041%

try

No Comments

No Known Activations