INDEX

Explanations

ed

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

atÃ³

-0.27

äºīåĪĽ

-0.25

ZONE

-0.24

 Ortiz

-0.24

crawler

-0.24

é«ĺæĺĤ

-0.23

 credibility

-0.23

 sickness

-0.23

getCell

-0.23

 Heaven

-0.23

POSITIVE LOGITS

zac

0.28

oliberal

0.27

æ§İ

0.27

ä¸Ģæīĭ

0.26

 Bannon

0.25

éĢı

0.25

buie

0.25

inant

0.25

æ³ķ

0.24

ONGL

0.24

Activations Density 0.002%

ed

No Comments

No Known Activations