© 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. 2834
    Prev
    Next
    INDEX
    Explanations

    say "demo"

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

    No Comments

    Negative Logits
     Rever
    -17.25
    dens
    -16.13
    equip
    -15.63
    oola
    -15.31
     Conserv
    -15.25
    -vis
    -14.94
     Gly
    -14.81
     conserv
    -14.75
    eeee
    -14.69
    arte
    -14.44
    POSITIVE LOGITS
     demo
    27.00
    demo
    25.50
    乙方
    25.38
     Demo
    25.25
     tech
    24.50
     admin
    23.88
    Demo
    23.75
     repo
    23.25
    /demo
    22.00
     config
    21.75
    Activations Density 0.026%

    No Known Activations