© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2053
    Prev
    Next
    INDEX
    Explanations

    say peripheral

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

    No Comments

    Negative Logits
    .ser
    -20.25
    丝
    -18.88
    (val
    -18.25
    义
    -17.75
    lege
    -17.75
    =val
    -17.75
    =obj
    -17.50
     val
    -17.25
    (img
    -17.00
     ser
    -16.88
    POSITIVE LOGITS
     peripheral
    31.13
    Peripheral
    28.25
     Peripheral
    27.88
     perimeter
    25.75
     peripherals
    24.00
    (per
    23.00
    周边
    22.75
    perms
    22.25
     Per
    22.13
    perm
    22.13
    Activations Density 0.058%

    No Known Activations