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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ever

-0.29

 People

-0.27

mis

-0.27

 Myth

-0.27

åº¦

-0.26

dis

-0.26

 intr

-0.25

lle

-0.25

cut

-0.25

fa

-0.25

POSITIVE LOGITS

isko

0.26

Ĳľç´¢

0.25

edList

0.25

æ¹ĺ

0.25

outed

0.24

lernen

0.24

ehr

0.24

'^

0.24

VRT

0.24

éĵ¤

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.