INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jective

-0.27

è·¨åº¦

-0.26

 same

-0.24

ä¸Ńå°ı

-0.24

etails

-0.23

illac

-0.23

entrant

-0.23

engkap

-0.23

Radians

-0.23

/basic

-0.23

POSITIVE LOGITS

arme

0.28

pring

0.28

åı¯çĸĳ

0.25

 nearing

0.25

hop

0.24

 Throne

0.24

sty

0.24

Hop

0.24

 Formation

0.24

Ð¾Ñı

0.24

Activations Density 0.009%

No Known Activations

This feature has no known activations.