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

 tÃ¼

-0.28

::__

-0.28

-ret

-0.28

ret

-0.27

ekte

-0.26

lags

-0.25

 Bans

-0.25

_ALIGN

-0.25

_RET

-0.24

 relat

-0.24

POSITIVE LOGITS

flate

0.28

å¯ĦãģĽ

0.27

èħĮ

0.25

erin

0.24

åĪĽ

0.24

dez

0.23

OCR

0.23

 broadcasts

0.23

ëĭ¨

0.23

roadcast

0.23

Activations Density 0.031%

No Known Activations

This feature has no known activations.