© 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. 1651
    Prev
    Next
    INDEX
    Explanations

    vector

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

    No Comments

    Negative Logits
     vector
    -55.00
     vectors
    -52.50
    vector
    -51.75
     VECTOR
    -50.50
    VECTOR
    -50.25
    Vectors
    -49.75
     Vector
    -48.25
    _vector
    -46.25
    Vector
    -46.00
     vect
    -45.50
    POSITIVE LOGITS
    黄金
    17.00
    anine
    15.94
    忙
    13.63
    福建
    13.63
    黄山
    13.44
    phony
    13.38
     Palace
    13.31
    Phone
    13.19
     Cardinal
    13.06
     cardinal
    13.06
    Activations Density 0.050%

    No Known Activations