INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð¾Ð»Ñı

-0.29

ä¸ºæľŁ

-0.26

Cad

-0.25

NEL

-0.25

unr

-0.24

uft

-0.24

çİĩè¾¾

-0.24

reach

-0.24

plotlib

-0.23

alcon

-0.23

POSITIVE LOGITS

âĨ©

0.32

/met

0.29

/person

0.26

 flats

0.25

ĶåĽŀ

0.25

Emp

0.25

éĢĢå½¹

0.24

ç¿ĺ

0.24

ðŁĵ¥

0.24

_override

0.24

Activations Density 0.139%

No Known Activations

This feature has no known activations.