© 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. 14944
    Prev
    Next
    INDEX
    Explanations

    any => from

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

    No Comments

    Negative Logits
     Depos
    -19.75
    GIS
    -17.25
    inges
    -17.13
    投资项目
    -17.13
    社会治理
    -16.75
    煉
    -15.50
    ök
    -15.31
    ỏi
    -15.00
     deposits
    -14.94
    _deposit
    -14.69
    POSITIVE LOGITS
    iasco
    14.75
     Bam
    14.13
     slump
    13.81
    맥
    13.44
    icated
    13.00
    全家
    12.88
    ioned
    12.81
    amba
    12.75
     pad
    12.75
     escape
    12.63
    Activations Density 0.040%

    No Known Activations