INDEX

Explanations

commit

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Debugger

-0.28

 Checker

-0.27

å¼ĢéĹ¨

-0.26

anker

-0.26

åĮĸçļĦ

-0.25

avern

-0.25

ç¨½

-0.24

.debian

-0.24

_checked

-0.24

.Navigator

-0.24

POSITIVE LOGITS

ÑĥÐ²

0.29

 things

0.28

 sensitive

0.27

ering

0.27

ens

0.27

 violent

0.27

things

0.27

 experience

0.26

ä¸Ģæ¬¡æĢ§

0.26

 successive

0.26

Activations Density 0.020%

commit

No Comments

No Known Activations