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

ÐľÐĺ

-0.27

çĦ¶æĺ¯

-0.27

 Rubin

-0.26

å²«

-0.25

SPORT

-0.25

 independents

-0.25

ĵį

-0.25

WithTitle

-0.25

 Banc

-0.25

ç¾¤éĩĮ

-0.24

POSITIVE LOGITS

mop

0.29

åģļäºĨ

0.29

-offset

0.28

oplay

0.28

rg

0.27

op

0.26

oma

0.26

æİ¢éĻ©

0.26

ran

0.25

contributors

0.25

Activations Density 0.009%

No Known Activations

This feature has no known activations.