INDEX

Explanations

code/file headers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĩįæķ´

-0.31

 reim

-0.28

çł´ç¢İ

-0.27

 ballo

-0.26

åķĨä¸ļéĵ¶è¡Į

-0.26

 reclaimed

-0.25

ê²¬

-0.25

 yell

-0.25

 burge

-0.25

åħ¶ä¸ŃåĮħæĭ¬

-0.24

POSITIVE LOGITS

ìŀħ

0.27

INO

0.27

LEM

0.27

æľºåħ³

0.27

evt

0.27

DEM

0.26

æ¸´

0.26

eria

0.26

ino

0.24

-make

0.24

Activations Density 0.012%

code/file headers

No Comments

No Known Activations