INDEX

Explanations

This

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Coins

-0.29

 strr

-0.27

 incons

-0.26

èĲ¦

-0.26

ä¸ºäºĨè®©

-0.25

 sadd

-0.24

[/

-0.24

vertising

-0.24

 palm

-0.24

ief

-0.24

POSITIVE LOGITS

åĽ½

0.25

ivial

0.25

-star

0.25

imen

0.24

åıĤ

0.24

pmat

0.24

 spot

0.24

 EITHER

0.24

enment

0.24

bmp

0.23

Activations Density 26.084%

This

No Comments

No Known Activations