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

Driving

-0.24

etter

-0.24

 ÐµÐ´Ð¸Ð½ÑģÑĤÐ²

-0.24

ariat

-0.23

Yin

-0.23

endas

-0.23

 misunder

-0.23

 Driving

-0.23

ocracy

-0.23

roads

-0.22

POSITIVE LOGITS

 upstream

0.28

xda

0.26

afe

0.25

 nÃ¤mlich

0.25

@\

0.25

ave

0.24

ä¹į

0.24

ILA

0.24

HAM

0.23

 downstream

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.