INDEX

Explanations

medicine

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

ousing

-0.31

acion

-0.28

åħīçħ§

-0.27

_MAN

-0.26

ä¸Ģèº«

-0.25

let

-0.25

assel

-0.24

emet

-0.23

	Namespace

-0.23

raction

-0.23

POSITIVE LOGITS

stadt

0.29

Defs

0.28

 America

0.28

pha

0.26

 volta

0.26

 america

0.26

tÄ±

0.25

.uni

0.25

America

0.25

pta

0.25

Activations Density 0.783%

medicine

No Comments

No Known Activations