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

enha

-0.26

ramework

-0.25

ÐºÑĢÐ°

-0.25

 Consultants

-0.24

/people

-0.24

-sl

-0.23

vara

-0.23

_CAST

-0.23

é¾Ħ

-0.23

çĴľ

-0.23

POSITIVE LOGITS

äºĳ

0.28

cloud

0.27

çĪª

0.27

éķ¶

0.27

fg

0.26

 cloud

0.26

anst

0.25

 Ð¼Ð°ÑĢÑĪ

0.24

æĺİç¡®è§Ħå®ļ

0.24

 Laur

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.