INDEX

Explanations

shapes

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

ÑĢÐµÐ¹

-0.28

æŃ¦åĬŁ

-0.27

æĸĹ

-0.25

ctal

-0.25

croll

-0.25

 splits

-0.24

ãĥĺãĥ«

-0.24

modal

-0.24

çıł

-0.24

etsk

-0.24

POSITIVE LOGITS

.constructor

0.27

 constructor

0.27

uality

0.26

.setLevel

0.26

console

0.25

è¿Ļç§įæĸ¹æ³ķ

0.25

 stressed

0.25

çĶµåİĤ

0.25

 console

0.25

constructed

0.25

Activations Density 0.001%

shapes

No Comments

No Known Activations