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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĩªå¦Ĥ

-0.28

orama

-0.27

pit

-0.27

exc

-0.25

caret

-0.24

aret

-0.24

 Sinclair

-0.24

 masse

-0.24

par

-0.23

sin

-0.23

POSITIVE LOGITS

 screenings

0.27

æ©Ľ

0.26

 tackles

0.24

 affirmative

0.24

 remot

0.24

 tackling

0.24

éļ¶å±ŀäºİ

0.23

AILS

0.23

å¤§äºº

0.23

 Germ

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.