© 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. 2924
    Prev
    Next
    INDEX
    Explanations

    say 改造

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

    No Comments

    Negative Logits
    .pet
    -20.75
    Pet
    -19.88
     Pet
    -19.00
    Pets
    -18.50
     Registered
    -18.25
     Mic
    -18.25
    Mic
    -17.88
    Mil
    -17.75
    mil
    -17.63
     Serial
    -16.88
    POSITIVE LOGITS
    改造
    48.25
     modification
    34.00
     modifier
    31.50
    modification
    31.25
    改
    30.75
    modify
    30.13
     modifications
    29.50
     Modifier
    28.88
     modify
    28.50
     Modification
    28.50
    Activations Density 0.050%

    No Known Activations