INDEX

Explanations

Technical, studies, work

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

orage

-0.28

è¿ľ

-0.27

_exchange

-0.27

äº¤æį¢

-0.27

 shadow

-0.27

 Chop

-0.26

 Exchange

-0.26

itim

-0.26

 Participant

-0.26

 Plate

-0.25

POSITIVE LOGITS

upy

0.33

isy

0.29

çī¹æ®ĬçļĦ

0.28

è¾ħå¯¼åĳĺ

0.28

ä¹ŁæĹłæ³ķ

0.26

ipy

0.26

ä¹Łæĺ¯ä¸Ģç§į

0.26

tester

0.25

 "),↵

0.25

estre

0.25

Activations Density 0.003%

Technical, studies, work

No Comments

No Known Activations