© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14890
    Prev
    Next
    INDEX
    Explanations

    multiplier

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

    No Comments

    Negative Logits
    Touches
    -17.25
    andles
    -16.63
    浔
    -16.50
     Tul
    -15.81
    Shar
    -15.06
    lake
    -14.94
    Lake
    -14.69
    ldata
    -14.69
     —↵↵
    -14.56
    love
    -14.50
    POSITIVE LOGITS
    ernet
    18.63
    spy
    18.38
    арат
    15.06
    xda
    15.00
     spy
    14.94
    yt
    14.94
     EntityType
    14.75
    chy
    14.63
    eti
    14.44
     yen
    14.31
    Activations Density 0.019%

    No Known Activations