INDEX

Explanations

Code and documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.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

-0.27

éĹ´æİ¥

-0.27

åĮºåĪ«

-0.26

 appearing

-0.25

å§Ķç»Ħç»ĩ

-0.25

Æ°á»Łng

-0.24

á»Ļt

-0.24

áº©u

-0.24

è¸¯

-0.24

 Ones

-0.24

POSITIVE LOGITS

 Billion

0.28

 accounts

0.26

hydrate

0.25

 role

0.24

 accomp

0.23

DV

0.23

ocs

0.23

é¡¾

0.23

 Nation

0.23

 billion

0.23

Activations Density 0.005%

Code and documentation

No Comments

No Known Activations