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

 boxed

-0.27

ç»ıçĲĨ

-0.27

 solid

-0.27

 Solid

-0.27

plays

-0.26

joy

-0.26

 condition

-0.26

.Master

-0.25

gw

-0.25

Solid

-0.24

POSITIVE LOGITS

bral

0.33

æľĶ

0.27

 Sequ

0.27

ESP

0.26

åĪº

0.26

ReadStream

0.26

æĿŁ

0.26

iture

0.26

æľ«

0.25

BOSE

0.25

Activations Density 53.879%

No Known Activations

This feature has no known activations.