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

ayas

-0.26

robat

-0.26

anst

-0.24

ackers

-0.24

çĻ»éĮĦ

-0.24

[curr

-0.24

 curled

-0.24

 REGISTER

-0.24

.har

-0.23

REGISTER

-0.23

POSITIVE LOGITS

esl

0.27

sin

0.26

atori

0.25

rs

0.25

olem

0.25

éļıçĿĢ

0.24

âĢ

0.24

arming

0.24

 beds

0.24

esen

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.