INDEX

Explanations

Gim

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

éĺ³

-0.29

JS

-0.26

pic

-0.26

yang

-0.26

Arch

-0.26

ients

-0.25

.Proxy

-0.24

lox

-0.24

éĻ½

-0.24

IG

-0.24

POSITIVE LOGITS

wi

0.30

 unpublished

0.26

łģ

0.26

(helper

0.26

æĲ¬è¿ģ

0.25

æ»ģ

0.25

 Essays

0.25

 ceremonies

0.25

åĩłçİĩ

0.25

æ¿Ĵ

0.25

Activations Density 0.788%

Gim

No Comments

No Known Activations