INDEX

Explanations

9

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç³ľ

-0.28

 Barcl

-0.27

 renew

-0.27

IGH

-0.26

çľ·

-0.26

çĭ±

-0.25

éĤ¸

-0.25

æĪ¿

-0.25

ç¥¨

-0.24

åĩĨæĹ¶

-0.24

POSITIVE LOGITS

çŁŃçŁŃ

0.29

éĽªå±±

0.27

 stem

0.26

-flex

0.25

 substituted

0.25

éĽª

0.24

VM

0.24

 FACT

0.24

underline

0.24

peg

0.24

Activations Density 0.027%

9

No Comments

No Known Activations