INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

çĿ¦

-0.26

 {}",

-0.25

ä½£

-0.24

çĿĽ

-0.24

 Earn

-0.24

ven

-0.24

“He

-0.24

æĸ°é²ľ

-0.24

 arson

-0.23

éĽĩä¸»

-0.23

POSITIVE LOGITS

patibility

0.28

éĽķ

0.28

å¸ĤåľºéľĢæ±Ĥ

0.27

{_

0.27

 priority

0.26

åĪ¨

0.26

priority

0.26

 adapt

0.25

breadcrumb

0.25

 depress

0.25

Activations Density 0.815%

No Known Activations

This feature has no known activations.