INDEX

Explanations

of

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Gut

-0.29

.rs

-0.26

utter

-0.26

lÃ¡

-0.25

xc

-0.25

æĵħ

-0.25

å»¶å®ī

-0.24

XC

-0.24

æī¹

-0.24

ä¸Ģæ¬¾

-0.24

POSITIVE LOGITS

esda

0.27

fills

0.26

 getCount

0.26

ESCO

0.25

legates

0.25

æŃ£ä¹ī

0.25

ÐµÐ²Ð¸Ñĩ

0.24

å¾ģéĽĨ

0.24

SError

0.24

-Jun

0.24

Activations Density 0.012%

of

No Comments

No Known Activations