© 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. 14226
    Prev
    Next
    INDEX
    Explanations

    say vector

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

    No Comments

    Negative Logits
    热水
    -17.75
    pectral
    -17.50
    循环经济
    -17.13
    水务
    -17.00
    温泉
    -16.88
    温
    -16.75
    电价
    -16.75
     XSS
    -16.75
    spect
    -16.50
    气温
    -16.50
    POSITIVE LOGITS
     vector
    27.38
     vectors
    25.63
     Vector
    23.25
     VECTOR
    22.88
    vector
    22.63
    _vector
    22.38
    _vectors
    22.38
    矢
    22.13
    VECTOR
    22.00
    -vector
    21.13
    Activations Density 0.166%

    No Known Activations