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

ly

-0.28

çķª

-0.27

aday

-0.27

ç¨¿

-0.26

åŀ©

-0.25

Ly

-0.25

ì¹ľ

-0.25

 jersey

-0.24

è½Ń

-0.24

à¸Ĥà¸²

-0.24

POSITIVE LOGITS

ild

0.29

Sul

0.24

 rais

0.24

 lexical

0.24

æĬ¥ç¤¾

0.24

 reason

0.23

odef

0.23

 exponential

0.23

 packets

0.23

 ------>

0.23

Activations Density 0.050%

No Known Activations

This feature has no known activations.