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

æŁ´

-0.31

çĤ¹

-0.27

-vars

-0.26

panse

-0.26

çŃ¾

-0.25

educ

-0.25

ä¼į

-0.25

å½ĵå¹´

-0.25

aud

-0.25

ÅŁt

-0.25

POSITIVE LOGITS

andalone

0.27

 principle

0.27

paces

0.26

 attacks

0.25

âĹ¢

0.25

é«ĺçŃīåŃ¦æł¡

0.25

æĻļæĬ¥

0.24

MDB

0.24

ections

0.24

.fm

0.23

Activations Density 0.008%

No Known Activations

This feature has no known activations.