© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14754
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    missive
    -16.25
    ie
    -13.63
    icide
    -13.31
    suming
    -13.25
    errupt
    -13.00
    ham
    -12.88
    sessionId
    -12.88
    小编一起
    -12.75
    ashi
    -12.50
    eries
    -12.19
    POSITIVE LOGITS
     Pru
    21.88
    ouro
    20.25
    UEST
    18.25
     wolf
    18.25
     Wolves
    18.13
     crater
    18.13
    stro
    18.13
    cko
    18.00
     Fountain
    18.00
    nton
    17.88
    Activations Density 0.110%

    No Known Activations