INDEX

Explanations

colons

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é£İæīĩ

-0.29

çĿ£åĬŀ

-0.26

PRI

-0.26

ä¸įè§ģäºĨ

-0.25

 Firewall

-0.25

è¢«åĳĬ

-0.24

ä¿¡æģ¯æĬ«éľ²

-0.24

åĩºåı£

-0.24

amera

-0.24

åĩ¡

-0.23

POSITIVE LOGITS

 status

0.28

orative

0.27

åĨµ

0.25

orf

0.25

ulence

0.25

 Cooke

0.24

 cultural

0.24

 perfect

0.24

enko

0.24

isans

0.24

Activations Density 0.351%

colons

No Comments

No Known Activations