INDEX

Explanations

technical and computer related

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

 Falk

-0.28

irie

-0.28

 Fresh

-0.26

Ãºt

-0.25

 Burn

-0.25

Up

-0.24

å¹´èµ·

-0.24

äººæ°ĳæľįåĬ¡

-0.24

 taxable

-0.24

 Probe

-0.24

POSITIVE LOGITS

 PROCUREMENT

0.30

ForObject

0.28

inform

0.28

éĢģåĩº

0.28

kill

0.25

iform

0.25

éº½

0.24

/vendor

0.24

åĳĬ

0.23

éĦĦ

0.23

Activations Density 0.015%

technical and computer related

No Comments

No Known Activations