INDEX

Explanations

Attempting, errors, or trying

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¾¿åĪ©

-0.29

acci

-0.27

ight

-0.25

æ£ł

-0.24

TestId

-0.24

ngr

-0.24

 conditional

-0.24

 parte

-0.24

éļĲ

-0.24

 ComVisible

-0.24

POSITIVE LOGITS

ÐµÐ²Ð¸Ñĩ

0.30

verbosity

0.27

 verbosity

0.26

ä¸ĢåĪĨéĴ±

0.26

çļĦæ¯Ķä¾ĭ

0.26

ç³Ĭ

0.26

è¾ĥå¤§çļĦ

0.25

 attempting

0.24

lect

0.24

å¡ĳ

0.24

Activations Density 0.455%

Attempting, errors, or trying

No Comments

No Known Activations