INDEX

Explanations

a

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_4.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.4.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿Ļæ®µ

-0.31

æ®µ

-0.27

æ¶Ī

-0.26

è¾Ī

-0.26

è±¡

-0.26

least

-0.26

á»ıi

-0.25

ãģĹãģ¦ãĤĤ

-0.25

è¿Ļå°±

-0.24

Least

-0.24

POSITIVE LOGITS

TRY

0.27

ldb

0.27

cru

0.25

 dumb

0.25

 earth

0.25

åĩĨåħ¥

0.25

çº³åħ¥

0.25

äºĴåĪ©

0.25

ucks

0.25

STRU

0.24

Activations Density 0.017%

a

No Comments

No Known Activations