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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĢıè§Ĩ

-0.25

è¯ķçĿĢ

-0.24

æ²¡éĶĻ

-0.24

kea

-0.23

ãĤ³ãĥ¼ãĥ

-0.23

ìĨ¡

-0.23

æĤļ

-0.23

éĢµ

-0.23

EMON

-0.23

æĤĦæĤĦ

-0.23

POSITIVE LOGITS

çģ«çĦ°

0.28

urn

0.27

-su

0.26

æ¼¾

0.25

åľ¨æĦı

0.25

æįķé±¼

0.25

æĴŀ

0.24

 rake

0.24

eo

0.24

[property

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.