INDEX

Explanations

printing

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

bid

-0.27

lsx

-0.25

æĥħ

-0.25

yer

-0.25

ilk

-0.25

ports

-0.24

 Schultz

-0.24

è½²

-0.24

afa

-0.23

arp

-0.23

POSITIVE LOGITS

inged

0.28

ngr

0.26

ervas

0.26

äº§ä¸ļéĵ¾

0.26

 depletion

0.26

æľįåĬ¡

0.24

ahan

0.24

æıĲè´¨

0.24

)-(

0.24

 recipro

0.24

Activations Density 0.014%

printing

No Comments

No Known Activations

printing

No Comments

No Known Activations