INDEX

Explanations

code and structured text

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

 ServiceException

-0.28

·»

-0.27

ç½¢äºĨ

-0.26

ç¢²

-0.26

odelist

-0.26

adro

-0.25

 dest

-0.25

æĭ¨

-0.24

èĦ¯

-0.24

èµĺ

-0.24

POSITIVE LOGITS

 banc

0.26

å²Ľå±¿

0.25

åŃ¦

0.25

opers

0.25

Ã©rica

0.25

erais

0.24

æĹ¶èĬĤ

0.24

 createState

0.24

eners

0.24

å¸¸è§Ħ

0.24

Activations Density 0.481%

code and structured text

No Comments

No Known Activations