INDEX

Explanations

of

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

åİŁæłĩé¢ĺ

-0.29

å¤ļæķ°

-0.28

Ã¼ss

-0.25

ÅĤa

-0.25

ä¸ĢæĹ¦

-0.24

ç¬¬äºĮç§į

-0.24

Descriptors

-0.23

>(()

-0.23

å½±åĵįåĬĽ

-0.23

leys

-0.23

POSITIVE LOGITS

RelativeTo

0.28

existing

0.27

ĺè®¤

0.26

DataRow

0.26

jud

0.26

 growing

0.25

illum

0.25

rit

0.25

rig

0.24

æĺĩ

0.24

Activations Density 0.010%

of

No Comments

No Known Activations