INDEX

Explanations

news/press releases

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

æĸ¹ä¾¿

-0.28

 concentr

-0.27

SED

-0.26

 convenient

-0.26

æŀľ

-0.26

 tidy

-0.25

 unsupported

-0.25

 concentrated

-0.24

ä¸įæĸ¹ä¾¿

-0.24

 bidi

-0.24

POSITIVE LOGITS

mach

0.28

mile

0.27

ä»ģ

0.26

machine

0.26

WR

0.25

 inflatable

0.25

éĢĢåĽŀ

0.25

enberg

0.25

æĢİä¹Īæł·

0.25

mor

0.24

Activations Density 0.003%

news/press releases

No Comments

No Known Activations