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

KER

-0.27

 Trom

-0.26

æīįçŁ¥éģĵ

-0.25

 SENT

-0.25

ernet

-0.25

tern

-0.25

wat

-0.24

SENT

-0.24

æĪĲåĬŁçļĦ

-0.24

wh

-0.24

POSITIVE LOGITS

å¤§äºº

0.29

ìĤ¬

0.29

atum

0.27

èĮĥ

0.25

 chic

0.25

odial

0.24

ãĤĴåıĸãĤĬ

0.24

æ¿Ĥ

0.24

_IDX

0.24

BorderStyle

0.23

Activations Density 34.004%

No Known Activations

This feature has no known activations.