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

aira

-0.27

-gradient

-0.26

berman

-0.25

.Progress

-0.25

agra

-0.25

sÄ±

-0.25

ungs

-0.25

éĹ´çļĦ

-0.24

ANEL

-0.24

æĸ¹éĿ¢çļĦ

-0.24

POSITIVE LOGITS

 Compound

0.30

Compound

0.29

 compound

0.29

serter

0.25

PO

0.25

TC

0.25

è·Įçł´

0.24

ve

0.24

.endswith

0.23

 rout

0.23

Activations Density 0.139%

No Known Activations

This feature has no known activations.