© 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. 14358
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     nâ
    -19.88
    "</
    -17.75
    ."</
    -17.63
    才是真正
    -17.38
     \""
    -17.00
    !".
    -17.00
    !↵↵↵↵↵↵
    -16.88
    !",↵
    -16.88
     UIF
    -16.75
    +"</
    -16.63
    POSITIVE LOGITS
    1
    19.50
    2
    17.75
    Q
    17.63
    4
    17.63
    3
    17.13
    5
    17.13
    Reg
    16.63
    reg
    16.63
    Micro
    16.13
    16.00
    Activations Density 0.056%

    No Known Activations