© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    say spect

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

    No Comments

    Negative Logits
    盒子
    -18.50
    编剧
    -18.25
    coder
    -16.75
    门户
    -16.25
    内科
    -16.13
    建筑师
    -16.13
     Builders
    -16.00
    Wr
    -16.00
    笑话
    -16.00
    codec
    -15.88
    POSITIVE LOGITS
     spectra
    30.88
     spectral
    30.25
     spectrum
    28.13
    spect
    27.88
     Spect
    27.88
     spect
    27.75
    _spectrum
    27.38
    谱
    27.25
     Spectrum
    26.63
     spectro
    26.25
    Activations Density 0.133%

    No Known Activations