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

 Incoming

-0.29

,Th

-0.28

 topo

-0.28

 incoming

-0.27

incoming

-0.25

_Service

-0.24

EFI

-0.24

=log

-0.24

__).

-0.23

Incoming

-0.23

POSITIVE LOGITS

çªģå¦Ĥåħ¶

0.28

quia

0.28

herits

0.26

æ®µ

0.26

ä¸ŃéĢĶ

0.25

å®īå±ħ

0.25

ä¸ĭéĿ¢å°±

0.25

anium

0.25

ience

0.24

 cours

0.24

Activations Density 0.096%

No Known Activations

This feature has no known activations.