INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.globalData

-0.25

 trá»ĭ

-0.24

 behaviour

-0.24

éĹ®è¯¢

-0.24

 Intr

-0.24

deal

-0.23

å¸ĸ

-0.23

_DISPATCH

-0.23

 launcher

-0.23

nu

-0.23

POSITIVE LOGITS

etrofit

0.30

otope

0.28

èĬ

0.28

etine

0.28

orro

0.27

ãĤĭãģŁãĤģãģ«

0.25

awei

0.25

gest

0.25

iert

0.25

etag

0.24

Activations Density 32.966%

No Known Activations

This feature has no known activations.