INDEX

Explanations

and

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

asive

-0.27

æĺ§

-0.25

.XR

-0.25

åı£è¯Ń

-0.24

nelle

-0.24

fos

-0.24

äº§çĶŁäºĨ

-0.24

MAL

-0.24

éĻĦ

-0.24

 solely

-0.23

POSITIVE LOGITS

ptime

0.29

allon

0.25

ä½Ĩä»ĸä»¬

0.25

ä¼ģä¸ļæıĲä¾Ľ

0.25

ä½Ĩæĺ¯å¯¹äºİ

0.24

èµłéĢģ

0.24

Token

0.24

scal

0.24

ChangeEvent

0.24

Bun

0.24

Activations Density 0.000%

and

No Comments

No Known Activations