INDEX

Explanations

author

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Podesta

-0.30

å¿«

-0.26

bage

-0.26

åİ¿å§Ķä¹¦è®°

-0.26

å¹²èĦĨ

-0.26

è¾Ł

-0.26

/popper

-0.25

orative

-0.25

 pains

-0.25

xAA

-0.25

POSITIVE LOGITS

/terms

0.26

ç»Łè®¡å±Ģ

0.25

 Factors

0.24

Shape

0.23

imed

0.23

Ã³r

0.23

kes

0.23

kes

0.23

 Ð¿Ð¾Ð»Ð¸

0.22

ä¹Łåıªæľī

0.22

Activations Density 0.001%

author

No Comments

No Known Activations