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

irie

-0.29

è´¡çĮ®åĬĽéĩı

-0.28

MCC

-0.25

`_

-0.24

éĽĨä¸Ń

-0.24

ipel

-0.24

unic

-0.24

æ²Ł

-0.24

_Params

-0.23

çĽ®ãģ«

-0.23

POSITIVE LOGITS

 devil

0.27

æµ·å³¡

0.26

çĽĽåħ¸

0.26

çľģåĨħ

0.25

 deviation

0.24

 twist

0.24

special

0.24

iel

0.24

acas

0.24

rending

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.