© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2191
    Prev
    Next
    INDEX
    Explanations

    say "philosophy"

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

    No Comments

    Negative Logits
    =req
    -16.25
    ationToken
    -16.00
    (req
    -15.44
    req
    -15.38
     Eq
    -15.19
    Berry
    -14.94
    curr
    -14.88
     curr
    -14.56
    .ev
    -14.38
     Sporting
    -14.13
    POSITIVE LOGITS
    哲学
    68.50
    Phil
    64.50
     philosophy
    63.25
     Philosophy
    63.25
    phil
    61.75
     Philosoph
    57.25
     philosophical
    55.25
     Phil
    54.75
     fil
    54.25
     philosoph
    53.00
    Activations Density 0.247%

    No Known Activations