© 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. 14526
    Prev
    Next
    INDEX
    Explanations

    bracketed text

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

    No Comments

    Negative Logits
     Weston
    -20.00
    莼
    -19.63
     Hern
    -19.50
    阚
    -19.25
    嫂
    -18.88
    Knife
    -18.50
    郦
    -18.50
     NavController
    -18.50
     hern
    -17.63
    蕺
    -17.50
    POSITIVE LOGITS
     di
    17.75
    ender
    16.25
     jig
    15.25
    di
    14.50
     d
    14.31
     ej
    14.31
    erd
    14.06
     Twig
    13.75
    im
    13.69
     Shar
    13.69
    Activations Density 0.868%

    No Known Activations