© 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. 15314
    Prev
    Next
    INDEX
    Explanations

    [title] => [name]

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

    No Comments

    Negative Logits
    enza
    -17.75
    XA
    -17.13
    mai
    -17.00
    abus
    -16.75
    кус
    -16.50
    KA
    -16.38
    ABL
    -16.13
    麻辣
    -16.13
    mts
    -16.13
    ERE
    -16.13
    POSITIVE LOGITS
     favoured
    15.88
    worth
    15.63
     favour
    15.25
     uyar
    13.50
     Spicer
    13.50
    历来
    13.25
    idden
    13.25
     deserving
    13.19
    addon
    13.06
     organisers
    13.00
    Activations Density 0.124%

    No Known Activations