INDEX

Explanations

or

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

ä¿±ä¹Ĳéĥ¨

-0.27

æĿĢäºº

-0.26

åĹŁ

-0.26

å¥½è±¡

-0.25

 Pods

-0.25

 hust

-0.25

 deposition

-0.25

assium

-0.25

 positives

-0.25

 clubs

-0.25

POSITIVE LOGITS

éľĢè¦ģ

0.27

vim

0.26

.forName

0.26

ins

0.25

breadcrumb

0.24

.tpl

0.24

uns

0.23

ampa

0.23

oco

0.23

_parser

0.23

Activations Density 0.003%

or

No Comments

No Known Activations