© 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. 15156
    Prev
    Next
    INDEX
    Explanations

    self

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

    No Comments

    Negative Logits
    afil
    -15.31
    idot
    -15.00
    蝶
    -14.69
     Bik
    -14.13
     bậc
    -14.06
    avad
    -14.00
     ByVal
    -13.94
     BigInteger
    -13.75
    Forgot
    -13.75
    PTY
    -13.69
    POSITIVE LOGITS
    onna
    17.63
    离
    17.13
     zipper
    16.25
    出境
    16.25
    orney
    15.44
     pressure
    15.44
    離
    15.44
    uppet
    15.38
    venge
    15.13
    ґ
    14.75
    Activations Density 0.728%

    No Known Activations