INDEX

Explanations

found

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

Į¨

-0.32

bis

-0.32

reat

-0.30

_misc

-0.28

dar

-0.28

 cross

-0.28

çŃı

-0.27

 Cross

-0.26

 triggered

-0.25

æĸ½

-0.25

POSITIVE LOGITS

èħĲè´¥

0.28

èħĲèļĢ

0.28

Disposable

0.27

å®ĺæĸ¹å¾®ä¿¡

0.27

ENN

0.27

å·¥å§Ķ

0.26

 Corruption

0.26

 scrimmage

0.25

iday

0.25

UIScreen

0.25

Activations Density 0.013%

found

No Comments

No Known Activations