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

ä¸ĩäºº

-0.29

ä¸ĩåĲį

-0.28

-flex

-0.28

åĪĹ

-0.25

äº²

-0.24

dent

-0.24

(Resources

-0.23

 Parad

-0.23

 xmlns

-0.23

etas

-0.23

POSITIVE LOGITS

itura

0.27

ina

0.27

attempt

0.27

geh

0.26

Ð¾Ð½Ð°

0.25

INA

0.25

 invasion

0.24

)||

0.24

 Gross

0.24

ilha

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.