INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otes

-0.28

pher

-0.26

å½ĵãģŁãĤĬ

-0.25

.per

-0.25

ainty

-0.24

-relative

-0.24

-employed

-0.24

æłı

-0.24

å±¥

-0.24

per

-0.23

POSITIVE LOGITS

äº²è¿ĳ

0.27

 cushions

0.27

moid

0.26

gor

0.26

å§¹

0.25

rug

0.25

Deque

0.25

åĽ½å®¶æłĩåĩĨ

0.25

pieces

0.24

nodeName

0.24

Activations Density 0.000%

No Comments

No Known Activations