INDEX

Explanations

given

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

æķĻä½ł

-0.26

ç»ıæµİæĬĢæľ¯

-0.26

tpl

-0.25

ä¹ĭäºº

-0.25

ç¿Ķ

-0.23

edException

-0.23

 FILES

-0.23

æĹ¥

-0.23

èĻ¹æ¡¥

-0.23

buster

-0.23

POSITIVE LOGITS

 that

0.33

the

0.32

mens

0.27

oton

0.25

 Storm

0.24

è¡Įä¸ļçļĦ

0.24

mak

0.24

 partition

0.23

 structural

0.23

 magn

0.23

Activations Density 0.207%

given

No Comments

No Known Activations