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

str

-0.28

ä¸¤ç±»

-0.27

å¥¥

-0.27

 pursued

-0.27

æī«

-0.26

èĤ²

-0.25

å¥§

-0.25

trigger

-0.25

¥¿

-0.24

-trigger

-0.23

POSITIVE LOGITS

è¤¥

0.28

ç¼¬

0.26

////////////////////////////////////////////////////////////////////////////////↵↵

0.25

ãģ³

0.24

åıĹå®³äºº

0.24

éĤ£ä¸ĢåĪ»

0.24

iage

0.24

xde

0.24

_Cmd

0.23

baum

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.