INDEX

Explanations

health and science

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ksi

-0.25

CEPTION

-0.24

 Concent

-0.24

esium

-0.24

 Sachs

-0.24

è¶¸

-0.23

 Burgess

-0.23

éĽĨä¸Ń

-0.23

fsp

-0.23

igger

-0.23

POSITIVE LOGITS

å¨ĺ

0.28

FEC

0.26

]-'

0.26

:req

0.25

nonce

0.25

ç§°ä¹ĭ

0.25

interopRequireDefault

0.25

umm

0.25

åĲĥçļĦ

0.24

Hed

0.24

Activations Density 0.002%

health and science

No Comments

No Known Activations