INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

OMIC

-0.28

 tighter

-0.28

ä¾

-0.28

-figure

-0.28

zes

-0.27

çĽİ

-0.26

-photo

-0.26

-decoration

-0.26

ä¾ĽéĶĢ

-0.25

uale

-0.24

POSITIVE LOGITS

equ

0.28

 fashion

0.26

äººéĹ´

0.24

 mann

0.24

 irre

0.24

æĴŃæĬ¥

0.24

èĴ¸åıĳ

0.24

èĵŁ

0.24

çĽ´æİ¥å½±åĵį

0.24

 equip

0.23

Activations Density 20.919%

No Known Activations

This feature has no known activations.