INDEX

Explanations

marketing and audiences

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

åĵĳ

-0.26

ONEY

-0.26

esium

-0.25

Bomb

-0.25

_vendor

-0.24

éĢıè§Ĩ

-0.24

è¹ĳ

-0.24

å¼±çĤ¹

-0.24

 tome

-0.23

{\

-0.23

POSITIVE LOGITS

åĬĽè¿ĺæĺ¯

0.28

 lÆ°á»£t

0.28

ä»Ģä¹Īæł·

0.27

indexPath

0.27

çĽĬ

0.26

instruction

0.26

 Instructions

0.26

engo

0.26

 Relief

0.26

 Instruction

0.26

Activations Density 0.001%

marketing and audiences

No Comments

No Known Activations