INDEX

Explanations

herpes

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

beh

-0.29

 manifesto

-0.27

LOT

-0.27

beh

-0.26

tem

-0.26

ous

-0.26

Beh

-0.26

azzi

-0.25

 flap

-0.25

rom

-0.25

POSITIVE LOGITS

æ±

0.31

 preventing

0.28

 Tá»Ń

0.27

 Prevent

0.27

çĥŁ

0.26

çħĻ

0.26

ãĥªãĥ³ãĤ¯

0.25

 diversified

0.25

_Err

0.25

Quotes

0.24

Activations Density 0.003%

herpes

No Comments

No Known Activations