INDEX

Explanations

Medical/anatomy texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¥ī

-0.28

elling

-0.26

algo

-0.26

 implode

-0.25

 originals

-0.25

irting

-0.25

 pledge

-0.25

åı¤èĢģçļĦ

-0.24

-na

-0.24

 commit

-0.24

POSITIVE LOGITS

areth

0.27

ayah

0.27

 includ

0.25

çĻ½éĵ¶

0.25

Solid

0.24

å±±åİ¿

0.23

 smith

0.23

onth

0.23

/API

0.23

 diss

0.23

Activations Density 1.301%

Medical/anatomy texts

No Comments

No Known Activations