INDEX

Explanations

nouns

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

 ÑģÑĩÐ¸ÑĤÐ°

-0.25

éĽªå±±

-0.24

å¤Ħ

-0.24

èį

-0.24

ummies

-0.23

æŃ»åĲİ

-0.23

åŃ

-0.23

 removeObject

-0.23

LowerCase

-0.23

LineStyle

-0.23

POSITIVE LOGITS

 tempered

0.27

 enhanced

0.26

enh

0.25

æĤ¨çļĦåŃ©åŃĲ

0.24

è¦Ĩ

0.24

Comple

0.24

INCLUDING

0.23

ä¸ªé¡¹çĽ®

0.23

nev

0.23

-Jun

0.23

Activations Density 0.001%

nouns

No Comments

No Known Activations