© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1712
    Prev
    Next
    INDEX
    Explanations

    [cloud] => [cloud]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cloud
    -67.00
    云
    -66.50
     clouds
    -62.75
     Cloud
    -59.50
    雲
    -59.00
    cloud
    -58.00
    Cloud
    -57.25
    _cloud
    -53.50
    -cloud
    -49.75
    云计算
    -49.00
    POSITIVE LOGITS
     political
    17.13
    Political
    16.88
    political
    16.13
    Santa
    16.00
    Ģ
    15.75
    motor
    15.56
    angling
    15.38
     stepper
    14.88
    DI
    14.75
    socket
    14.50
    Activations Density 0.130%

    No Known Activations