INDEX

Explanations

sensory

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

ÑĥÑĩÐ°

-0.33

èĥ½æī¾åĪ°

-0.28

atypes

-0.28

.writeFileSync

-0.26

 EntityState

-0.26

æµģãĤĮ

-0.25

é²ľè¡Ģ

-0.24

>NN

-0.24

è¿Ļè¯Ŀ

-0.24

Towards

-0.23

POSITIVE LOGITS

éĹŃ

0.29

 nond

0.28

åį³å°Ĩ

0.27

ho

0.27

late

0.26

 relative

0.26

legen

0.26

MAP

0.25

 passing

0.24

 strateg

0.24

Activations Density 0.261%

sensory

No Comments

No Known Activations