© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1224
    Prev
    Next
    INDEX
    Explanations

    spectral

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     spiritual
    -35.50
    Spirit
    -35.25
    精神
    -35.00
    spirit
    -34.25
     Spectrum
    -32.75
     Spiritual
    -32.75
     spectral
    -30.38
     spirit
    -30.38
     spiritually
    -30.13
     spectrum
    -29.88
    POSITIVE LOGITS
    calc
    16.75
     calc
    16.13
    .calc
    15.94
    肉类
    15.63
    _cal
    15.50
    _CALC
    15.38
    _calc
    15.06
     CALC
    14.50
     calcium
    14.25
    Calc
    14.25
    Activations Density 0.195%

    No Known Activations