© 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. 2003
    Prev
    Next
    INDEX
    Explanations

    [λ] => [λ]

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

    No Comments

    Negative Logits
    计算
    -17.13
     computation
    -16.88
    計算
    -16.50
    元
    -15.69
     calculation
    -15.31
     law
    -14.81
     Calculation
    -14.63
     computations
    -14.06
     mentally
    -13.81
    eteor
    -13.69
    POSITIVE LOGITS
    酸
    22.13
     Oil
    20.50
     oil
    20.50
    Oil
    20.25
     mac
    19.88
    Mac
    19.63
    油
    19.63
    伊斯兰
    19.25
     acid
    18.75
    台
    18.38
    Activations Density 0.295%

    No Known Activations