INDEX

Explanations

treatment

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WithValue

-0.25

distribution

-0.24

XVI

-0.23

Distribution

-0.23

_HI

-0.23

ä¼¤çĹħ

-0.23

ç³ķ

-0.23

 Distributed

-0.23

 Ball

-0.23

çĸĹ

-0.23

POSITIVE LOGITS

ç´§å¼ł

0.28

Ð²ÐµÑģ

0.27

åĳ½

0.27

pom

0.26

åķĨ

0.26

è¦ģç´§

0.26

çĿ¿

0.25

oll

0.25

ilm

0.25

 floor

0.23

Activations Density 0.017%

treatment

No Comments

No Known Activations