INDEX

Explanations

while

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

ercul

-0.27

é«ĺé¢ĳ

-0.25

éĥ¨ç½²

-0.25

['.

-0.25

ehr

-0.24

 poly

-0.24

 gigs

-0.24

,assign

-0.24

ÑıÑĤÐ¸

-0.24

 Ð±ÐµÑģ

-0.23

POSITIVE LOGITS

smith

0.31

ä¼

0.29

 yourselves

0.28

rod

0.27

arov

0.26

æĤ¨çļĦåŃ©åŃĲ

0.26

_VC

0.25

orsk

0.25

datap

0.25

 youre

0.25

Activations Density 0.002%

while

No Comments

No Known Activations