INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sling

-0.29

psilon

-0.28

ä¸ľæµ·

-0.25

sl

-0.25

nemonic

-0.24

 slideshow

-0.24

cher

-0.24

RESSION

-0.24

ngthen

-0.23

issors

-0.23

POSITIVE LOGITS

pageTitle

0.25

æ½

0.25

opt

0.25

Ã©d

0.25

ou

0.25

alt

0.25

å³°åĢ¼

0.24

×ª×Ļ×Ļ×Ŀ

0.24

æĸ¥

0.24

ç¬Ķ

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.