INDEX

Explanations

R

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ErrorException

-0.27

åľ£

-0.26

aptor

-0.26

ç¾Ĭ

-0.26

åį³å°ĨåĪ°æĿ¥

-0.25

 stripslashes

-0.25

 ë¬¼ë¡ł

-0.25

 updater

-0.25

stor

-0.24

_cov

-0.24

POSITIVE LOGITS

herited

0.31

çªį

0.27

ç»¼åĲĪ

0.27

æķĻä½ł

0.27

:mm

0.27

fin

0.26

Ä±ÅŁ

0.26

ushi

0.25

esen

0.25

fin

0.25

Activations Density 0.012%

R

No Comments

No Known Activations