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

 each

-0.28

ttp

-0.27

each

-0.27

 disp

-0.27

ËĲ

-0.25

 mach

-0.24

/styles

-0.23

nist

-0.23

mnt

-0.23

 community

-0.23

POSITIVE LOGITS

Ä±m

0.29

ÃŃtica

0.29

ÅĽl

0.26

etta

0.26

åı£æ°´

0.26

Ä±t

0.26

å¦»

0.26

FLT

0.25

FDA

0.25

comings

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.