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

[opt

-0.24

 Confeder

-0.24

ArgumentException

-0.24

rary

-0.24

åı£è¢ĭ

-0.23

verbs

-0.23

æĴŀ

-0.23

ãĥĻãĥ³

-0.23

:'

-0.23

,ev

-0.23

POSITIVE LOGITS

åħ¨ç¨ĭ

0.28

 tons

0.27

ä¸Ģä½ĵ

0.26

ç»Ŀ

0.25

å½ĵåīį

0.25

 masses

0.24

hex

0.24

ÑĥÐ»ÑĮ

0.24

Thr

0.23

åĲĦçľģ

0.23

Activations Density 0.095%

No Known Activations

This feature has no known activations.