© 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. 1595
    Prev
    Next
    INDEX
    Explanations

    say "cal"

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

    No Comments

    Negative Logits
    绿豆
    -15.38
    json
    -14.81
     json
    -13.94
    ubuntu
    -13.81
    DOT
    -13.44
    炷
    -13.25
    alent
    -13.13
     pint
    -13.00
    chers
    -12.94
     DOT
    -12.88
    POSITIVE LOGITS
    钙
    26.38
     calcium
    23.88
     California
    20.88
    _cal
    20.63
    California
    20.50
     Calcium
    20.25
    -cal
    19.88
    四川
    19.13
    Phones
    18.75
    佛教
    18.75
    Activations Density 0.311%

    No Known Activations