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

çĻ¾

-0.25

å¢©

-0.25

sand

-0.25

isor

-0.25

isNull

-0.24

å²Ľ

-0.24

det

-0.24

sme

-0.24

 Mata

-0.23

 supervise

-0.23

POSITIVE LOGITS

 recur

0.26

ä¸ªäººè§ĤçĤ¹

0.26

lax

0.25

éĹ©

0.25

 ones

0.24

']->

0.24

è¡½

0.23

=title

0.23

 themselves

0.23

äººéĥ½

0.23

Activations Density 0.015%

No Known Activations

This feature has no known activations.