INDEX

Explanations

exceptions and qualifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

juven

-0.28

æĹ¨

-0.27

gone

-0.26

å±ĭéĩĮ

-0.26

 Meaning

-0.25

ç¦ģåĮº

-0.25

æĸ°æĶ¿

-0.25

aversal

-0.25

 spos

-0.25

etros

-0.24

POSITIVE LOGITS

åŁºç¡Ģ

0.27

 Ð¼Ð°ÑĤ

0.26

pal

0.26

 ever

0.25

ÑĥÐ³Ð»

0.24

arih

0.24

èģĶåĲĪä¼ļ

0.24

åĪ¶å®ļäºĨ

0.24

.inc

0.24

PAL

0.23

Activations Density 0.012%

exceptions and qualifications

No Comments

No Known Activations