INDEX

Explanations

computer code and text

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

lass

-0.28

è®°å¿Ĩ

-0.28

æŀ·

-0.27

æĮ½åĽŀ

-0.26

uala

-0.25

ensa

-0.25

 suffix

-0.25

Controller

-0.25

rie

-0.24

ä»·

-0.24

POSITIVE LOGITS

.toObject

0.28

 Roku

0.26

hints

0.26

 Redistribution

0.25

 narc

0.25

 Croat

0.24

çīĪæĿĥæīĢæľī

0.24

peak

0.24

çī¹æ®Ĭ

0.24

éĥĬ

0.24

Activations Density 0.036%

computer code and text

No Comments

No Known Activations