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

ouver

-0.25

å¹´ä»£

-0.25

åĿ¦

-0.24

 Portfolio

-0.24

Specifications

-0.24

åĨįè¯´

-0.24

cox

-0.24

''↵

-0.23

Portfolio

-0.23

↵

-0.23

POSITIVE LOGITS

ä»ª

0.29

èį¨

0.28

abler

0.27

 maÃ±ana

0.25

hoc

0.25

gre

0.25

ocity

0.24

ãĥģãĥ£ãĥ¼

0.24

_fps

0.24

aÃ±a

0.24

Activations Density 0.099%

No Known Activations

This feature has no known activations.