INDEX

Explanations

the

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

çīµå¼ķ

-0.28

xF

-0.27

EDI

-0.27

Leading

-0.27

æľĢé«ĺçļĦ

-0.26

å·¥ä½ľæľºåĪ¶

-0.25

xf

-0.25

 mechanisms

-0.24

 derog

-0.24

 Leading

-0.24

POSITIVE LOGITS

andles

0.29

å¤·

0.28

 matcher

0.25

opic

0.25

åŃ£åº¦

0.25

icted

0.25

çĶ¨åľ°

0.24

æ££

0.24

çĶŁçĶŁ

0.24

plode

0.23

Activations Density 0.013%

the

No Comments

No Known Activations