INDEX

Explanations

Ass

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

åĬ¿

-0.29

arg

-0.27

inks

-0.27

off

-0.26

è¶ĭ

-0.25

á»ı

-0.25

 FEATURE

-0.24

ocr

-0.24

=@"

-0.24

ox

-0.24

POSITIVE LOGITS

ylie

0.29

yll

0.29

ceipt

0.26

SError

0.26

ansi

0.25

 Shoe

0.25

iani

0.25

dec

0.25

.innerHeight

0.24

lÃ¶

0.24

Activations Density 0.036%

Ass

No Known Activations