INDEX

Explanations

f

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ESP

-0.27

/sm

-0.26

Ð¾ÑģÑĤÐµÐ¹

-0.25

Smy

-0.25

åĮ»åĬ¡äººåĳĺ

-0.25

å¾ĭ

-0.24

rial

-0.24

è´¿èµĤ

-0.24

trys

-0.24

SEA

-0.24

POSITIVE LOGITS

è¶ħæłĩ

0.26

IRECT

0.24

ModifiedDate

0.24

creativecommons

0.24

áº¿

0.23

elig

0.23

-rate

0.23

lname

0.23

inee

0.23

standing

0.23

Activations Density 0.000%

f

No Comments

No Known Activations