INDEX

Explanations

ask/beg

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

stack

-0.31

ctor

-0.27

ients

-0.27

 system

-0.25

coat

-0.25

èĲ½

-0.25

eam

-0.25

esco

-0.24

mo

-0.24

Mae

-0.23

POSITIVE LOGITS

 permission

0.46

permission

0.39

.permission

0.38

è®¸

0.38

è¨±

0.38

æĿĥéĻĲ

0.36

 perm

0.36

perm

0.36

Perm

0.35

Permission

0.34

Activations Density 0.004%

ask/beg

No Known Activations