INDEX

Explanations

Ye

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

ãģ¡ãģ¯

-0.30

æĪ·

-0.28

Kel

-0.27

 getInt

-0.27

errupted

-0.26

ä¼¤

-0.25

ious

-0.25

peaker

-0.25

æīĺ

-0.24

éĿĴæĺ¥

-0.24

POSITIVE LOGITS

åĽºå®ļçļĦ

0.26

ngle

0.26

Phones

0.26

 fries

0.26

å¤§çº²

0.25

snow

0.25

unos

0.24

aware

0.24

 snow

0.24

segments

0.24

Activations Density 0.175%

Ye

No Comments

No Known Activations