INDEX

Explanations

saying/telling

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

acies

-0.28

folder

-0.26

 folder

-0.26

(norm

-0.26

ç¢İçīĩ

-0.26

åĽ¢

-0.26

 Prim

-0.25

 fragment

-0.25

cum

-0.25

fork

-0.25

POSITIVE LOGITS

ä¸įæİĴéĻ¤

0.27

ervisor

0.26

Ð¿Ð¾Ñĩ

0.25

rique

0.24

-series

0.24

rompt

0.24

 convertible

0.24

Pil

0.24

beb

0.24

aram

0.23

Activations Density 0.001%

saying/telling

No Comments

No Known Activations