INDEX

Explanations

wall

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

èĦ±

-0.29

apur

-0.28

éĺµ

-0.27

æĹłåĬĽ

-0.25

AGR

-0.25

á»ĳt

-0.25

æ·¬

-0.25

*</

-0.25

æīİæł¹

-0.24

èĥĮ

-0.24

POSITIVE LOGITS

åı£æ°´

0.30

ioned

0.27

 accounted

0.26

å¾ĪæŃ£å¸¸

0.26

Cake

0.25

aylight

0.25

 vÃŃ

0.24

 blanket

0.24

ivant

0.24

łéĻ¤

0.23

Activations Density 0.001%

wall

No Comments

No Known Activations