INDEX

Explanations

and

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ponge

-0.27

 attrs

-0.26

ooled

-0.25

etr

-0.25

inion

-0.24

StateException

-0.24

pled

-0.24

enga

-0.24

 retention

-0.24

fluence

-0.23

POSITIVE LOGITS

åĬ³

0.29

 dict

0.27

Say

0.26

ê²¬

0.26

 somewhat

0.26

éĥ½éľĢè¦ģ

0.26

bbing

0.26

brig

0.25

ocker

0.25

artz

0.25

Activations Density 0.011%

and

No Comments

No Known Activations