© 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. 15322
    Prev
    Next
    INDEX
    Explanations

    [2] => [2]

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

    No Comments

    Negative Logits
    adian
    -20.50
    asted
    -19.00
    wdx
    -18.75
    elines
    -18.63
     Trọng
    -18.13
    Pid
    -17.88
    едь
    -17.75
    ailed
    -17.25
    edException
    -17.25
    (tid
    -16.88
    POSITIVE LOGITS
    .CL
    15.63
     chambers
    13.19
    VERS
    13.13
    脆
    13.00
    BU
    13.00
    .Cl
    13.00
    clone
    12.69
    .cl
    12.50
    克
    12.50
    ɾ
    12.44
    Activations Density 0.065%

    No Known Activations