INDEX

Explanations

Code and math

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

getVar

-0.27

 compil

-0.25

dep

-0.25

çĸĨ

-0.25

 Functional

-0.25

under

-0.25

saw

-0.24

íĤ·

-0.24

ule

-0.24

éģ²

-0.24

POSITIVE LOGITS

Ser

0.27

èļ¤

0.27

raf

0.27

cher

0.26

quer

0.26

åĵģ

0.26

pliers

0.25

èĽ®

0.25

åĬ£

0.25

æ³¡

0.24

Activations Density 0.006%

Code and math

No Comments

No Known Activations