© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2616
    Prev
    Next
    INDEX
    Explanations

    say 范

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

    No Comments

    Negative Logits
     Cons
    -19.25
     mel
    -17.75
     Mur
    -17.25
    Cons
    -17.13
    kel
    -16.88
     kel
    -16.75
    cons
    -16.13
    Perl
    -15.88
     Kel
    -15.88
    _cons
    -15.63
    POSITIVE LOGITS
    范
    79.50
     Sam
    48.50
    Sam
    42.00
     param
    40.75
    (param
    38.75
     sam
    38.50
    sam
    35.25
    =obj
    34.25
     norm
    34.00
    义
    33.75
    Activations Density 0.055%

    No Known Activations