INDEX

Explanations

Medical and scientific terms

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

nets

-0.27

 reconcile

-0.26

atr

-0.26

indle

-0.25

 dwell

-0.25

hex

-0.25

IAL

-0.25

 Sect

-0.24

ias

-0.24

æīĵäºĨ

-0.24

POSITIVE LOGITS

nement

0.26

nton

0.25

aca

0.25

åĲ¸

0.25

 proto

0.25

èĭ¦

0.24

acao

0.23

æĶ¹éĿ©åıĳå±ķ

0.23

_require

0.23

 Pluto

0.23

Activations Density 0.004%

Medical and scientific terms

No Comments

No Known Activations