INDEX

Explanations

Names

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

::$

-0.30

cers

-0.29

ĵį

-0.28

__$

-0.27

è®¿

-0.25

 dads

-0.25

 hooked

-0.25

AtPath

-0.24

itals

-0.24

è£¸

-0.23

POSITIVE LOGITS

æľŁåĨħ

0.33

éĵĽ

0.29

van

0.25

è®¢

0.24

åĲįçīĮ

0.24

éĹ´éļĶ

0.24

 perfect

0.24

 ether

0.24

ickets

0.24

cstdio

0.24

Activations Density 0.111%

Names

No Comments

No Known Activations