© 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. 15130
    Prev
    Next
    INDEX
    Explanations

    [has] => [number]

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

    No Comments

    Negative Logits
    福特
    -20.63
     Cros
    -19.00
    HY
    -17.63
    GPC
    -17.38
     Hank
    -17.00
    OLF
    -16.88
    增值
    -16.88
    破裂
    -16.88
    Ford
    -16.75
    lsi
    -16.75
    POSITIVE LOGITS
    (chan
    14.06
    lane
    13.25
    .djangoproject
    12.94
    igan
    12.94
    倩
    12.75
     Choir
    12.63
    党支部
    12.63
    _chan
    12.63
    风筝
    12.56
    unsch
    12.50
    Activations Density 0.037%

    No Known Activations