© 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. 14442
    Prev
    Next
    INDEX
    Explanations

    [hex] => a

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

    No Comments

    Negative Logits
     bào
    -23.00
    подоб
    -20.50
     Bust
    -20.00
     Kitt
    -19.63
    RIPT
    -19.63
    HORT
    -19.50
     caul
    -19.50
    plist
    -19.25
    oppers
    -19.00
    ritch
    -19.00
    POSITIVE LOGITS
    colon
    14.25
     gridColumn
    12.50
     wolf
    12.13
     Wolf
    12.13
    eyJ
    11.94
     Falcon
    11.94
     OL
    11.63
    lac
    11.25
     colon
    11.13
     Leon
    11.13
    Activations Density 0.006%

    No Known Activations