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

stim

-0.28

çĺ¢

-0.25

cmp

-0.25

ÇĶ

-0.25

 breakout

-0.25

FromArray

-0.25

fed

-0.25

èĤ¢

-0.24

arez

-0.24

 distr

-0.24

POSITIVE LOGITS

nen

0.25

ÑıÑĤ

0.25

 INTERVAL

0.25

åİŁåĽłä¹ĭä¸Ģ

0.25

vertise

0.24

åłħ

0.24

é¢ł

0.24

æĪ¿éĹ´éĩĮ

0.23

¢

0.23

[:-

0.23

Activations Density 0.008%

No Known Activations

This feature has no known activations.