INDEX

Explanations

computer networking

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

 keyValue

-0.27

_dicts

-0.26

 Parade

-0.25

cliffe

-0.25

sonian

-0.25

lish

-0.25

ilik

-0.25

å¤§å®Ĺ

-0.24

OMET

-0.24

 impro

-0.24

POSITIVE LOGITS

avings

0.28

icontrol

0.27

icap

0.26

gc

0.25

å¿ĥè·³

0.24

æİ¥åĲ¬

0.24

Capt

0.24

.InteropServices

0.24

 Stick

0.23

ë·°

0.23

Activations Density 0.017%

computer networking

No Comments

No Known Activations