INDEX

Explanations

Noisy data

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

çŁ³èĨı

-0.29

 Flask

-0.27

Inn

-0.25

_INF

-0.24

ervations

-0.24

ä¼¸æīĭ

-0.24

pel

-0.23

Fle

-0.23

éħĴç²¾

-0.23

INF

-0.23

POSITIVE LOGITS

å¯Įæ°ĳ

0.29

lic

0.27

inium

0.27

-custom

0.26

ileges

0.26

 customize

0.25

shaw

0.24

recur

0.24

 sacram

0.24

æµĭè¯ķ

0.23

Activations Density 0.001%

Noisy data

No Comments

No Known Activations