INDEX

Explanations

enger

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

Ang

-0.29

åĭĩå£«

-0.27

Jin

-0.27

touch

-0.25

Ang

-0.25

Kut

-0.25

ç§¯æ°´

-0.24

*&

-0.24

ħĮ

-0.24

roc

-0.24

POSITIVE LOGITS

ERAL

0.30

åıĳå±ķæ¨¡å¼ı

0.25

eral

0.25

è¯¦ç»Ĩä»ĭç»į

0.25

 isOpen

0.24

åıĳå±ķçļĦ

0.24

iece

0.24

 vÃ¤

0.24

otropic

0.24

itarian

0.23

Activations Density 0.085%

enger

No Comments

No Known Activations