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

æĤĦçĦ¶

-0.28

anas

-0.28

different

-0.26

aphore

-0.26

asing

-0.26

anine

-0.25

ailable

-0.25

éĶ²

-0.25

())).

-0.25

())↵↵↵

-0.25

POSITIVE LOGITS

å®ļçĤ¹

0.26

åĢĻéĢī

0.26

Ìģ

0.24

é¼į

0.24

_GB

0.24

Ð»Ð°Ð´

0.23

æ§Ĭ

0.23

ç»ĪçĤ¹

0.23

jq

0.23

cit

0.23

Activations Density 0.007%

No Known Activations

This feature has no known activations.