© 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. 13909
    Prev
    Next
    INDEX
    Explanations

    say "proof"

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

    No Comments

    Negative Logits
     projects
    -28.50
     project
    -27.38
     Projects
    -27.00
    项目
    -26.75
    项目的
    -26.13
    projects
    -25.75
     Project
    -25.75
    Projects
    -24.00
     PROJECT
    -23.50
    Project
    -23.13
    POSITIVE LOGITS
    证
    21.50
    證
    20.88
    验证
    20.00
    -proof
    19.50
    取
    18.63
    proof
    18.50
     proof
    18.38
     Take
    18.13
    taken
    18.13
    _proof
    18.00
    Activations Density 0.846%

    No Known Activations