INDEX

Explanations

outh

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

edList

-0.29

::<

-0.28

nemonic

-0.27

/\

-0.25

CriticalSection

-0.25

ning

-0.24

 straw

-0.24

 Exist

-0.24

 javax

-0.24

omaly

-0.24

POSITIVE LOGITS

ure

0.28

éĻį

0.28

ilitation

0.28

itas

0.26

care

0.26

åĬ¡

0.25

æĸ¹ä¾¿

0.24

ouri

0.24

 efficiencies

0.24

åį°

0.24

Activations Density 0.001%

outh

No Comments

No Known Activations