© 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. 14608
    Prev
    Next
    INDEX
    Explanations

    say arrow

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

    No Comments

    Negative Logits
    _sid
    -23.13
    avis
    -22.50
    sid
    -21.75
    Sid
    -21.38
     sca
    -21.38
    酰
    -20.63
    alar
    -20.25
    埽
    -20.13
    awl
    -19.63
    .aw
    -19.25
    POSITIVE LOGITS
     Hend
    19.13
    bens
    18.50
     Concert
    17.38
    HK
    17.13
    rug
    16.38
    ben
    16.38
    茹
    16.38
    benh
    16.13
     Hatch
    16.13
     Hemp
    15.75
    Activations Density 0.931%

    No Known Activations