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

 constit

-0.27

 Chattanooga

-0.27

cents

-0.27

 Coleman

-0.25

 proportional

-0.25

 defaultProps

-0.24

 centralized

-0.24

æ²¡æĶ¶

-0.23

box

-0.23

 defaultValue

-0.23

POSITIVE LOGITS

[('

0.27

ypes

0.26

hin

0.25

avior

0.24

[*

0.24

rance

0.24

å¼Ĥè®®

0.23

Ð²Ð¾Ð·

0.23

åĵĦ

0.23

 Bench

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.