INDEX

Explanations

medical treatments and studies

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

quier

-0.27

medi

-0.26

åĩº

-0.25

 thoughtful

-0.25

out

-0.24

 mask

-0.24

 opposite

-0.24

 duly

-0.24

riet

-0.24

 Hughes

-0.23

POSITIVE LOGITS

stands

0.29

standen

0.29

ansom

0.27

dana

0.27

AINS

0.27

isl

0.27

ains

0.26

rek

0.26

OMEM

0.25

å¼¹

0.25

Activations Density 0.001%

medical treatments and studies

No Comments

No Known Activations