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

tit

-0.27

can

-0.25

èģĶéĤ¦

-0.25

rale

-0.25

 buffer

-0.25

vier

-0.24

Buffer

-0.24

ate

-0.24

 context

-0.24

æ¶Īè´¹èĢħçļĦ

-0.24

POSITIVE LOGITS

OfYear

0.26

 Brotherhood

0.26

-years

0.24

 jose

0.24

-thinking

0.24

ÐµÐ´ÑĮ

0.24

($__

0.23

thalm

0.23

_cmos

0.23

 THINK

0.23

Activations Density 0.007%

No Known Activations

This feature has no known activations.