INDEX

Explanations

frequency

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

çº¿ä¸Ĭçº¿ä¸ĭ

-0.26

Away

-0.25

åĳĬè¯īå¤§å®¶

-0.25

æīįèĥ½

-0.25

 Assoc

-0.24

éģĴ

-0.24

vr

-0.24

-standard

-0.24

 stairs

-0.24

ç¹ģèį£

-0.24

POSITIVE LOGITS

putation

0.27

ACP

0.26

fef

0.26

ewan

0.25

DataContext

0.25

ppe

0.25

DAC

0.25

fÃ¤ll

0.25

udad

0.24

theid

0.24

Activations Density 0.015%

frequency

No Comments

No Known Activations