© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14340
    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
    okie
    -18.00
    kan
    -17.75
    嗪
    -17.63
    激
    -17.38
    kit
    -17.38
    kas
    -16.88
    Lock
    -16.75
    斯基
    -16.50
    anky
    -16.38
    лан
    -16.38
    POSITIVE LOGITS
     Dover
    19.63
    氘
    17.88
    uger
    17.88
     Goth
    17.50
     Worce
    17.38
    eft
    16.50
     Geoffrey
    16.50
     ged
    16.38
     Caesar
    16.25
    hte
    16.25
    Activations Density 0.088%

    No Known Activations