© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    say demo words

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

    No Comments

    Negative Logits
    eq
    -17.88
    meth
    -16.38
     eq
    -16.25
    甲
    -16.13
     capitals
    -16.13
    趾
    -15.88
     mut
    -15.88
     vec
    -15.81
    丝
    -15.75
     Meth
    -15.25
    POSITIVE LOGITS
     demo
    67.00
     Demon
    66.00
    Demon
    65.00
     demonstration
    64.00
    demo
    64.00
     Demo
    63.25
    Demo
    63.25
     demonstrations
    59.25
     demos
    58.75
    示范
    58.25
    Activations Density 0.251%

    No Known Activations