INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

èĥĮçĿĢ

-0.28

 organizational

-0.27

ser

-0.24

-span

-0.24

 print

-0.24

åħīèį£

-0.24

 span

-0.24

èĥĮ

-0.24

ãĤ»ãĥ«

-0.24

‘

-0.23

POSITIVE LOGITS

omba

0.28

(MenuItem

0.28

angelog

0.27

æĪĲéķ¿

0.27

éŁ³

0.27

rawler

0.25

çĦ¶

0.25

phony

0.25

éłĪ

0.24

fang

0.23

Activations Density 34.158%

No Known Activations

This feature has no known activations.