INDEX

Explanations

evidence and justification

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

 face

-0.29

carbon

-0.29

 carbon

-0.27

 intern

-0.27

ton

-0.26

 internal

-0.26

 accomplished

-0.26

rum

-0.26

 origin

-0.25

onda

-0.25

POSITIVE LOGITS

sbin

0.28

ltd

0.27

 guerr

0.26

ifetime

0.25

-FIRST

0.25

+'

0.24

åŁı

0.24

ROID

0.24

/includes

0.24

æİ¨åĩºçļĦ

0.23

Activations Density 0.000%

evidence and justification

No Comments

No Known Activations