INDEX

Explanations

visualize

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

kir

-0.28

other

-0.27

è´£ä»»åĪ¶

-0.26

enses

-0.26

;br

-0.25

WAY

-0.25

å»ºè®¾é¡¹çĽ®

-0.25

iris

-0.25

 ofType

-0.24

æ¡¤

-0.24

POSITIVE LOGITS

é³ŀ

0.26

æŀķå¤´

0.26

_Internal

0.25

Screenshot

0.25

é²į

0.25

 Sims

0.25

atz

0.24

é¸¡

0.24

æ£į

0.24

 bedtime

0.24

Activations Density 0.037%

visualize

No Comments

No Known Activations