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

suite

-0.28

amer

-0.27

avier

-0.26

åĥµ

-0.26

atural

-0.25

ader

-0.25

olo

-0.24

æ¯ĶåĪĨ

-0.24

olver

-0.24

 PMID

-0.24

POSITIVE LOGITS

EDA

0.25

_letters

0.25

æĬ«

0.24

èģĶæĥ³

0.24

,'

0.24

åĩĨå¤ĩ

0.24

'[

0.23

alic

0.23

æĩĤå¾Ĺ

0.23

 transforms

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.