© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    numer => numer

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

    No Comments

    Negative Logits
     numerical
    -45.75
     Numer
    -42.50
     numer
    -41.25
     numeric
    -39.00
    Numer
    -37.50
    _numer
    -37.25
    numer
    -37.00
    numeric
    -37.00
     Numeric
    -36.50
    Numeric
    -36.25
    POSITIVE LOGITS
    执法
    14.50
    Di
    14.50
    风格
    14.25
    山
    14.19
    MLE
    14.13
    MethodInfo
    14.06
    违法行为
    14.06
    -di
    14.06
     steel
    14.00
    石油
    14.00
    Activations Density 0.149%

    No Known Activations