INDEX

Explanations

is

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

iks

-0.28

 arrival

-0.27

Rem

-0.27

HAM

-0.27

æ±

-0.26

ARING

-0.26

unw

-0.26

rem

-0.26

.Has

-0.26

Ð¸ÑĤÐ°

-0.26

POSITIVE LOGITS

 capital

0.27

å±Ģéĥ¨

0.24

 Capital

0.24

 Burgess

0.24

otation

0.24

 Pandora

0.23

 bold

0.23

agner

0.23

 brace

0.23

anal

0.23

Activations Density 0.004%

is

No Known Activations