INDEX

Explanations

trauma

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

ibase

-0.32

reich

-0.27

gou

-0.25

bic

-0.25

åħ±å»º

-0.24

éĽªå±±

-0.24

GetObject

-0.24

irim

-0.24

imenti

-0.23

://%

-0.23

POSITIVE LOGITS

ynthesis

0.26

æĸĩåĮĸåĴĮ

0.26

Licensed

0.25

 tá»ĳ

0.25

yps

0.25

\Factory

0.24

YLE

0.24

è¹ĭ

0.24

 Stard

0.24

 curated

0.23

Activations Density 0.002%

trauma

No Comments

No Known Activations