© 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. 14695
    Prev
    Next
    INDEX
    Explanations

    section numbers

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

    No Comments

    Negative Logits
     indictment
    -17.38
    dropout
    -15.56
    濕
    -15.56
     dry
    -15.44
     dripping
    -15.38
     Pipeline
    -15.25
     SearchResult
    -14.88
    浍
    -14.88
     Worce
    -14.88
    alary
    -14.88
    POSITIVE LOGITS
    技术
    17.25
     �
    16.50
     �
    16.13
    基本
    16.00
    反
    16.00
    读
    16.00
    增
    15.88
    扩展
    15.75
     �
    15.75
    目
    15.56
    Activations Density 0.082%

    No Known Activations