© 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. 2478
    Prev
    Next
    INDEX
    Explanations

    say "phil"

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

    No Comments

    Negative Logits
    det
    -17.63
     Det
    -16.25
    Det
    -16.13
    тал
    -16.00
    DET
    -15.56
    (det
    -15.38
    特派员
    -15.19
    曲线
    -15.00
     det
    -14.38
    _det
    -14.31
    POSITIVE LOGITS
    Phil
    75.50
     Phil
    75.00
     fil
    67.50
    phil
    66.50
    Fil
    63.25
     Fil
    63.25
     φ
    63.25
     phil
    61.50
    (fil
    61.25
    哲学
    60.00
    Activations Density 0.129%

    No Known Activations