© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    say "regression"

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

    No Comments

    Negative Logits
    facility
    -16.63
    argo
    -16.50
     Facility
    -14.81
    kap
    -14.69
    Fac
    -14.63
     ngu
    -14.44
    rium
    -14.31
    iro
    -14.25
    颉
    -14.25
    .fac
    -14.13
    POSITIVE LOGITS
    reg
    65.00
     regression
    64.50
     reg
    64.50
     Reg
    60.25
     Regression
    59.75
    (reg
    59.50
    	reg
    58.00
    Regression
    57.00
     regress
    56.25
    Reg
    54.75
    Activations Density 0.070%

    No Known Activations