INDEX

Explanations

Code, paths, and licenses

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

leta

-0.30

ugins

-0.29

éĵ

-0.29

ä»¤

-0.28

itters

-0.26

vinc

-0.25

åŃ¦

-0.24

ÐĽÐ¬

-0.24

itant

-0.24

rot

-0.23

POSITIVE LOGITS

çľŁ

0.30

/files

0.27

ä¸įåľ¨ä¹İ

0.26

 demÃ¡s

0.26

çļĦåĬĽéĩı

0.25

è¯įæĿ¡

0.25

 Archived

0.25

elo

0.25

!<

0.24

æīĢä»¥åľ¨

0.24

Activations Density 0.011%

Code, paths, and licenses

No Known Activations