INDEX

Explanations

computer programming

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

Not in Any Lists

No Comments

Negative Logits

ioni

-0.28

pym

-0.26

å°½åĬĽ

-0.25

.cms

-0.25

 intermitt

-0.25

.selenium

-0.25

 PropTypes

-0.24

 sulfate

-0.23

å·´åŁº

-0.23

æĶ¾ä¸ĭ

-0.22

POSITIVE LOGITS

lim

0.26

-exc

0.25

aud

0.25

culo

0.24

voy

0.24

id

0.24

è§ī

0.24

ä¸ºå®¢æĪ·

0.23

aunch

0.23

cul

0.23

Activations Density 0.005%

computer programming

No Comments

No Known Activations