INDEX

Explanations

medical topics

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

studio

-0.28

 Ã©p

-0.25

 studio

-0.25

committed

-0.24

hardt

-0.24

 explorer

-0.24

composer

-0.24

 Lage

-0.23

åľ°æĿ¿

-0.23

 composer

-0.23

POSITIVE LOGITS

ipple

0.28

ushing

0.27

arms

0.27

çĽ´

0.27

\Requests

0.25

{}\

0.25

VML

0.25

bear

0.25

(curl

0.24

Ø´Ùĩ

0.24

Activations Density 0.001%

medical topics

No Comments

No Known Activations