INDEX

Explanations

-sharing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AIL

-0.30

éĶĻè¿ĩäºĨ

-0.26

Sle

-0.26

éĿ

-0.26

 :↵↵↵↵

-0.25

å¹¿æĴŃ

-0.24

å¿½è§Ĩ

-0.24

ÇĶ

-0.24

 radio

-0.23

SError

-0.23

POSITIVE LOGITS

åĪ¶åº¦

0.28

urm

0.26

 doInBackground

0.25

 UIManager

0.25

 getContentPane

0.25

çº¬

0.24

ssql

0.24

åī§æľ¬

0.23

 dads

0.23

 qualifying

0.23

Activations Density 0.005%

-sharing

No Comments

No Known Activations