INDEX

Explanations

programming and technical references

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

fas

-0.27

 opportunity

-0.25

.AutoScaleMode

-0.25

::*

-0.25

ÐµÐ½Ð½Ð¾

-0.25

 face

-0.25

.addHandler

-0.25

 incorrect

-0.24

à¸²à¸°

-0.24

restricted

-0.24

POSITIVE LOGITS

 Wins

0.26

ëŀĢ

0.26

 Peaks

0.25

(man

0.25

usage

0.24

leo

0.24

è´¯éĢļ

0.24

 dilig

0.24

 Rentals

0.24

liga

0.24

Activations Density 0.955%

programming and technical references

No Known Activations