INDEX

Explanations

there

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

åŁ¹è®ŃæľºæŀĦ

-0.29

ç¨į

-0.29

æ¯Ĵ

-0.26

ä¸įçĦ¶

-0.26

 Prospect

-0.26

Ø¬Ùĩ

-0.25

Fact

-0.25

ius

-0.25

åŃ¦åĳĺ

-0.24

ez

-0.24

POSITIVE LOGITS

ulary

0.28

ocop

0.28

 appendString

0.28

Instrument

0.28

ombre

0.26

è¯´æĺİä¹¦

0.26

æ¼Ķå¥ı

0.26

 Glam

0.26

ilter

0.26

 Instrument

0.26

Activations Density 0.004%

there

No Comments

No Known Activations