INDEX

Explanations

Services/service

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 toast

-0.33

apest

-0.29

 tack

-0.27

æĪĴ

-0.27

caffold

-0.26

æīĢåľ¨

-0.26

æľĢé«ĺ

-0.25

æľīæĦıæĢĿçļĦ

-0.24

 themselves

-0.24

 egreg

-0.24

POSITIVE LOGITS

ailer

0.28

 userModel

0.27

ertas

0.26

 landed

0.25

 HomeController

0.25

 imageSize

0.25

Ign

0.24

èĽ°

0.24

boa

0.24

 fores

0.24

Activations Density 0.003%

Services/service

No Comments

No Known Activations