INDEX

Explanations

ae

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

orris

-0.30

 loading

-0.29

umb

-0.29

UMB

-0.27

 shadow

-0.27

umb

-0.26

 saving

-0.26

åĴ½åĸī

-0.25

 humming

-0.25

-shadow

-0.25

POSITIVE LOGITS

è¯´å®ŀ

0.32

è¯´å¾Ĺ

0.29

è¯Ŀ

0.26

adan

0.26

agged

0.26

çľ¼çļ®

0.26

andy

0.26

RowAt

0.25

ä¿®ä¸º

0.25

è°ı

0.25

Activations Density 0.012%

ae

No Comments

No Known Activations