INDEX

Explanations

its

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ŃåĽ½å¸Ĥåľº

-0.26

SourceType

-0.26

resentation

-0.26

ç

-0.25

æµ·è¿Ĳ

-0.25

"('

-0.25

çĥ¹é¥ª

-0.25

.extern

-0.24

 miesz

-0.24

 Profession

-0.24

POSITIVE LOGITS

bard

0.28

å·®ä¸įå¤ļ

0.26

craft

0.26

 tá»Ļc

0.25

å·¡

0.25

 Ð¿Ð¾Ð»Ñĥ

0.24

 adress

0.24

interactive

0.24

Interceptor

0.23

.fm

0.23

Activations Density 0.320%

its

No Comments

No Known Activations