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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15760
    Prev
    Next
    INDEX
    Explanations

    say cloud

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

    No Comments

    Negative Logits
    $core
    -18.50
    xon
    -18.13
     bond
    -17.63
     Axe
    -16.63
    年薪
    -16.38
    扳
    -16.25
    /repos
    -16.13
    \core
    -15.56
     Heritage
    -15.38
     magistrate
    -15.38
    POSITIVE LOGITS
     cloud
    34.75
     clouds
    34.25
     Cloud
    32.50
    云
    32.00
    Cloud
    31.63
    cloud
    31.50
    雲
    30.88
    _cloud
    30.13
    .Cloud
    27.13
    -cloud
    26.88
    Activations Density 0.239%

    No Known Activations