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

 Nose

-0.26

è°Ĳ

-0.26

-scenes

-0.26

éħµ

-0.25

 perfect

-0.25

nar

-0.25

é¼»

-0.25

ovan

-0.25

plr

-0.24

 clearance

-0.24

POSITIVE LOGITS

_/

0.27

äº«çĶ¨

0.27

 Late

0.26

çķĮ

0.24

 somew

0.24

excerpt

0.23

 unidentified

0.23

æ²ı

0.23

 late

0.23

è¿Ľåº¦

0.23

Activations Density 0.018%

No Known Activations

This feature has no known activations.