© 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. 15250
    Prev
    Next
    INDEX
    Explanations

    URLs

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

    No Comments

    Negative Logits
    词
    -18.25
    物资
    -16.63
    英镑
    -16.13
    模型
    -16.13
    searchModel
    -16.13
    议案
    -15.81
    _subject
    -15.75
    研究报告
    -15.56
    涂料
    -15.50
    行长
    -15.44
    POSITIVE LOGITS
    ky
    16.50
    zac
    16.38
    raf
    15.56
    iz
    15.38
    mor
    15.25
    maps
    15.06
    bs
    14.94
    anto
    14.88
    nicos
    14.88
    chr
    14.75
    Activations Density 0.062%

    No Known Activations