© 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. 15037
    Prev
    Next
    INDEX
    Explanations

    [name] => [name]

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

    No Comments

    Negative Logits
    rita
    -22.50
    va
    -20.00
    REA
    -20.00
    arth
    -19.88
    atha
    -18.88
    vat
    -18.63
    arra
    -18.00
    lice
    -18.00
    vä
    -17.88
    口袋
    -17.63
    POSITIVE LOGITS
     Broncos
    16.63
    聘
    15.38
     Zig
    15.25
     проб
    15.13
     sniff
    14.81
    沾
    14.69
     Dob
    14.56
     enn
    14.31
     Lang
    14.31
     Daisy
    14.25
    Activations Density 0.779%

    No Known Activations