INDEX

Explanations

IDs or Designations

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

Negative Logits

åĬ£

-0.28

IDO

-0.28

ialect

-0.26

åŃļ

-0.25

umper

-0.25

illo

-0.24

 liá»ĩu

-0.24

(trim

-0.23

RESSION

-0.23

trimmed

-0.23

POSITIVE LOGITS

ename

0.26

arrow

0.26

èıĬ

0.25

 anything

0.25

ES

0.24

æĬĬå®ĥ

0.24

 physical

0.24

ker

0.24

anything

0.23

è½»

0.23

Activations Density 0.003%

IDs or Designations

No Known Activations