INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

iare

-0.26

rollers

-0.25

è·µ

-0.25

_DETECT

-0.25

enance

-0.25

åĬ©éķ¿

-0.24

':č↵

-0.24

âĺŁ

-0.24

å¥³æĺŁ

-0.24

.'</

-0.24

POSITIVE LOGITS

land

0.27

 critical

0.26

Ground

0.26

æ±

0.26

lands

0.25

 ground

0.25

 critically

0.25

axter

0.25

 Builder

0.25

 Grand

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.