INDEX

Explanations

was

np_max-act · gemini-2.0-flash

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

 Agency

-0.27

Agency

-0.26

ExecutionContext

-0.26

aggio

-0.25

:UI

-0.24

 steril

-0.24

Cities

-0.24

âİľ

-0.23

Vol

-0.23

ä¹ĭåŁİ

-0.23

POSITIVE LOGITS

ouple

0.28

æ¨£

0.27

 Bout

0.26

duit

0.24

 nodded

0.23

yas

0.23

yz

0.23

 bout

0.23

quis

0.23

 FUNC

0.23

Activations Density 0.004%

was

No Comments

No Known Activations