© 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. 14259
    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
    報
    -18.88
    Reporting
    -17.38
     Reporter
    -16.88
     Reporting
    -16.88
     reporter
    -16.63
    报送
    -16.38
     Messaging
    -16.00
    UserCode
    -15.88
    zbek
    -15.63
    报
    -15.44
    POSITIVE LOGITS
    证明
    42.50
     proofs
    41.00
     proof
    40.25
     arguments
    37.75
     argument
    36.75
    论证
    36.50
    證明
    36.25
     Proof
    36.00
    proof
    35.50
    argument
    35.25
    Activations Density 1.412%

    No Known Activations