© 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. 2846
    Prev
    Next
    INDEX
    Explanations

    say generic

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

    No Comments

    Negative Logits
    帝国
    -15.88
    帝
    -15.31
     melt
    -15.00
    妈妈
    -14.75
    quee
    -14.50
    antee
    -14.19
    嫔
    -14.06
    っ�
    -13.63
    企
    -13.63
    _profit
    -13.50
    POSITIVE LOGITS
    代
    75.50
     Generic
    62.25
    Generic
    60.00
    generic
    59.75
     generic
    59.75
    -generic
    52.25
     gener
    52.25
     Gener
    52.00
    _generic
    51.75
     generics
    51.50
    Activations Density 0.082%

    No Known Activations