INDEX

Explanations

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olec

-0.28

å»ºåįİ

-0.27

 TLabel

-0.27

ernote

-0.26

reed

-0.26

á»Ńa

-0.25

fuse

-0.25

AllWindows

-0.25

â¾Ĭ

-0.25

Po

-0.25

POSITIVE LOGITS

nier

0.27

unts

0.26

èľ»

0.26

Pitch

0.26

åŃĺåľ¨çļĦ

0.25

xies

0.24

 surface

0.24

ICES

0.24

Int

0.24

çľŁäºº

0.23

Activations Density 0.156%

code snippets

No Comments

No Known Activations