INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

çĶ©

-0.26

 Shine

-0.25

Ð»Ð¸Ð²

-0.25

.cleanup

-0.25

cro

-0.25

sum

-0.25

 Socialist

-0.24

ä¸ļ

-0.24

ayout

-0.24

æıĲæĭĶ

-0.24

POSITIVE LOGITS

duk

0.26

nty

0.26

bsolute

0.25

mods

0.24

åĿĽ

0.24

urrenc

0.23

 derivation

0.23

åīįçº¿

0.23

lander

0.23

 rootReducer

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.