© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14740
    Prev
    Next
    INDEX
    Explanations

    section labels

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

    No Comments

    Negative Logits
     �
    -15.63
     �
    -15.25
    在
    -15.06
     �
    -14.75
    乐
    -14.00
     �
    -13.75
     �
    -13.56
     �
    -13.44
    al
    -13.13
     �
    -12.88
    POSITIVE LOGITS
    OAD
    19.13
    YE
    18.00
     Retrofit
    17.50
    项目建设
    16.75
    鞘
    16.63
    纡
    16.50
    Ye
    16.25
    投資
    16.13
     provinc
    16.00
     rif
    16.00
    Activations Density 0.147%

    No Known Activations