INDEX

Explanations

management

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

eries

-0.29

rub

-0.28

åŁł

-0.26

 business

-0.25

åºķä¸ĭ

-0.25

 carefully

-0.25

 BUSINESS

-0.25

 careful

-0.24

_MI

-0.24

Produces

-0.24

POSITIVE LOGITS

ÑĪÐ¸Ð²

0.29

è¢«æīĵ

0.25

itÃ¤

0.25

gaard

0.25

 rendre

0.24

ç¼ķ

0.24

èį·

0.24

aghan

0.24

StackTrace

0.24

iker

0.24

Activations Density 0.022%

management

No Comments

No Known Activations