INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ĢåĪĨ

-0.29

cir

-0.28

unya

-0.28

æ·ĭ

-0.27

Cir

-0.27

 tweeted

-0.26

 circulated

-0.24

æŀĿ

-0.24

circ

-0.24

ç¤¼

-0.24

POSITIVE LOGITS

 ModelState

0.26

 compared

0.26

 comparison

0.25

Comparer

0.25

åĴĢ

0.24

_comparison

0.24

()",

0.24

 pilot

0.24

su

0.24

ation

0.23

Activations Density 4.390%

No Known Activations

This feature has no known activations.