INDEX

Explanations

data collection

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

éĹ®çŃĶ

-0.26

↵

-0.25

eliness

-0.25

 rules

-0.24

tons

-0.24

åĩ»

-0.24

ç¡®

-0.24

 clutch

-0.24

 diá»ĩn

-0.23

.toByteArray

-0.23

POSITIVE LOGITS

 leaking

0.31

ä¸įé«ĺ

0.27

afx

0.26

pei

0.26

æ³ł

0.25

ä¸įåĩº

0.25

 pepp

0.25

POV

0.24

è´ŁéĿ¢å½±åĵį

0.24

ä¹Łå°±æĺ¯è¯´

0.24

Activations Density 0.023%

data collection

No Comments

No Known Activations