INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¤®

-0.25

istency

-0.25

ogenerated

-0.24

ç§¯æŀģæĢ§

-0.24

 GeschÃ¤

-0.24

asticsearch

-0.23

inement

-0.23

rip

-0.23

 Whitney

-0.23

setWidth

-0.23

POSITIVE LOGITS

çŃĶ

0.26

Æ°a

0.26

Ø§Ø±Ø¯

0.24

opian

0.24

ucc

0.24

{})

0.24

çīĮ

0.23

âĨĴ

0.23

eyes

0.23

bia

0.23

Activations Density 0.008%

No Known Activations

This feature has no known activations.