INDEX

Explanations

organizations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 licensors

-0.28

 Families

-0.27

orsch

-0.27

azzo

-0.27

 synchronization

-0.25

 Rockefeller

-0.25

çªł

-0.25

aits

-0.24

ynth

-0.24

/xml

-0.23

POSITIVE LOGITS

iche

0.26

èĢ³

0.26

mostat

0.25

<source

0.25

pir

0.25

icha

0.24

æľ«

0.24

ä»¥ä¸ĬçļĦ

0.23

eral

0.23

wig

0.23

Activations Density 0.000%

organizations

No Comments

No Known Activations