INDEX

Explanations

technical documentation/troubleshooting

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

azi

-0.29

åĶ¿

-0.29

datatable

-0.27

çĽ´è§Ĥ

-0.26

çļĦæ¯Ķä¾ĭ

-0.25

åıĤèĤ¡

-0.25

TestData

-0.24

coc

-0.24

avax

-0.24

AZY

-0.23

POSITIVE LOGITS

ely

0.28

æľīäºĨ

0.27

 reven

0.27

elt

0.25

 Composite

0.25

Composite

0.24

éĽį

0.24

æĸ½å·¥

0.24

pect

0.24

 elastic

0.24

Activations Density 0.002%

technical documentation/troubleshooting

No Comments

No Known Activations