INDEX

Explanations

formal written text

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

less

-0.27

NM

-0.26

Nap

-0.26

 Grace

-0.26

erv

-0.26

-less

-0.25

æ»Ķ

-0.25

cest

-0.25

nap

-0.25

 desn

-0.25

POSITIVE LOGITS

iddles

0.28

åĭĴ

0.27

tier

0.26

ired

0.26

åĴĮæĶ¯æĮģ

0.26

rawid

0.25

äºĽä»Ģä¹Ī

0.25

çīĪæĿĥå½ĴåİŁ

0.25

á»Ī

0.25

.JsonProperty

0.24

Activations Density 0.001%

formal written text

No Comments

No Known Activations