INDEX

Explanations

code/programming

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç¥Ŀ

-0.31

Wa

-0.28

 unlocked

-0.28

 Cert

-0.27

ç©´

-0.27

ulling

-0.27

abo

-0.26

sweet

-0.26

hone

-0.26

aber

-0.26

POSITIVE LOGITS

ç©ºæ°Ķè´¨éĩı

0.32

inations

0.30

 pollution

0.29

å¤§æ°Ķ

0.29

ç©ºæ°Ķ

0.29

 atmos

0.29

 executions

0.28

æī¬å°ĺ

0.27

getNext

0.27

 polluted

0.27

Activations Density 0.000%

code/programming

No Comments

No Known Activations