INDEX

Explanations

compared

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åįıåĬŀ

-0.27

ting

-0.25

 --------------------------------

-0.25

aven

-0.25

æº¢

-0.25

ç¾İä¸½

-0.25

mentions

-0.24

ä¹Łå¸ĮæľĽ

-0.23

ç¾İä¸½çļĦ

-0.23

Beautiful

-0.23

POSITIVE LOGITS

quete

0.30

antly

0.26

ole

0.24

$?

0.24

oul

0.24

ipped

0.24

illy

0.24

aal

0.24

ataka

0.23

 decency

0.23

Activations Density 0.194%

compared

No Comments

No Known Activations