INDEX

Explanations

recordings or logs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

ä¸Ńå¿ĥåŁİå¸Ĥ

-0.28

ewise

-0.26

çº¬

-0.25

-scripts

-0.25

å¤§åıĳ

-0.24

ç»ıçº¬

-0.24

TEMPL

-0.24

ific

-0.24

åıĳè¨Ģäºº

-0.24

idge

-0.23

POSITIVE LOGITS

0.27

pone

0.27

ocking

0.25

quier

0.25

 Binder

0.25

å®ķ

0.24

å¤§çĨĬçĮ«

0.24

 Planet

0.24

ÙĦØ³

0.23

lt

0.23

Activations Density 2.989%

recordings or logs

No Comments

No Known Activations