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

 Manor

-0.25

 cursed

-0.23

 ÐĳÑĢ

-0.23

è¦ģåģļå¥½

-0.23

odic

-0.23

ÐºÐ°Ð·Ð°ÑĤÑĮ

-0.23

åĪ¶å®ļäºĨ

-0.22

OUTH

-0.22

asan

-0.22

nard

-0.22

POSITIVE LOGITS

èĢĥçĤ¹

0.24

Indicator

0.24

 Charlottesville

0.24

Ã¨ge

0.23

 immobil

0.23

ä¹Ļçĥ¯

0.23

ENTS

0.23

Eli

0.23

 together

0.23

belt

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.