© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14059
    Prev
    Next
    INDEX
    Explanations

    say "key"

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

    No Comments

    Negative Logits
    폭
    -18.13
    mue
    -16.88
     PROGRAM
    -16.75
    .jquery
    -16.25
    ários
    -16.13
    类产品
    -16.13
    communic
    -15.81
    opard
    -15.63
    年以上
    -15.63
    样品
    -15.56
    POSITIVE LOGITS
     keys
    42.75
    键
    42.00
     key
    41.00
    key
    39.25
    keys
    39.00
     Key
    38.25
    Key
    38.00
    =key
    37.25
    _key
    36.50
    -key
    36.25
    Activations Density 0.387%

    No Known Activations