© 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. 14282
    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
    系统
    -56.75
    系统的
    -55.25
     system
    -54.75
    system
    -52.00
     systems
    -51.00
    systems
    -49.50
     System
    -49.25
    システム
    -48.75
    _system
    -48.50
    -system
    -47.75
    POSITIVE LOGITS
    货源
    18.50
    证明
    18.13
     proof
    17.13
    Proof
    16.75
     prove
    16.75
    練
    16.75
    签约
    16.63
    -proof
    16.50
     items
    16.38
    proof
    16.13
    Activations Density 1.033%

    No Known Activations