INDEX

Explanations

"Big" followed by something

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

mage

-0.27

áºŃn

-0.27

åīĤéĩı

-0.26

æĢ»éĺŁ

-0.26

 toxin

-0.26

æĺ¯ä¸Ģä»¶

-0.25

å³°åĢ¼

-0.25

"{{

-0.25

edList

-0.24

 Pistol

-0.24

POSITIVE LOGITS

ny

0.28

-den

0.26

æĳ©

0.25

 respectively

0.25

bru

0.24

lene

0.24

æĵį

0.24

sil

0.24

den

0.24

UST

0.24

Activations Density 0.001%

"Big" followed by something

No Comments

No Known Activations