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

Negative Logits

æĢ»åħ¬åı¸

-0.28

 Reputation

-0.28

ureka

-0.28

ffffffff

-0.26

swer

-0.26

 ActionController

-0.26

ç«ĭ

-0.25

Rated

-0.25

æīĺ

-0.24

æĺİç¡®æıĲåĩº

-0.24

POSITIVE LOGITS

Âł

0.27

 Soft

0.27

ÂłÂłÂłÂł

0.26

 pole

0.25

cre

0.25

peak

0.24

 Musk

0.24

åį´åıĪ

0.24

 Âł

0.24

 peak

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.