© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1212
    Prev
    Next
    INDEX
    Explanations

    [float] => [floaters]

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

    No Comments

    Negative Logits
     float
    -47.50
     floats
    -45.00
    float
    -45.00
    浮
    -43.25
     Float
    -43.00
    Float
    -42.50
     floating
    -42.25
    FLOAT
    -39.50
     FLOAT
    -39.50
     Floating
    -39.00
    POSITIVE LOGITS
    音乐
    18.13
    音樂
    17.88
     Surgical
    16.50
    手术
    16.00
    usic
    15.81
    utan
    15.81
     song
    15.75
    琴
    15.63
     surgery
    15.56
     Song
    15.50
    Activations Density 0.112%

    No Known Activations