INDEX

Explanations

STIs and medical terminology

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

 Shiv

-0.28

èĻŀ

-0.26

Nm

-0.25

ording

-0.25

	catch

-0.25

æµªè´¹

-0.24

åİĭ

-0.24

Cp

-0.24

outh

-0.24

åĬªåĬĽ

-0.24

POSITIVE LOGITS

bab

0.28

ãģ¾ãĤĮ

0.26

efault

0.26

udge

0.26

ccione

0.25

 sweeping

0.25

 typeof

0.25

emaakt

0.24

edited

0.23

 moderate

0.23

Activations Density 0.001%

STIs and medical terminology

No Comments

No Known Activations