© 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. 2535
    Prev
    Next
    INDEX
    Explanations

    anti

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

    No Comments

    Negative Logits
     capital
    -19.75
    递
    -17.88
    capital
    -17.50
     CAPITAL
    -17.25
     Capital
    -15.69
    -capital
    -15.63
    总队
    -15.50
     recursion
    -15.38
     app
    -15.38
    еч
    -15.31
    POSITIVE LOGITS
    防
    75.50
     anti
    48.75
     Anti
    46.50
    Anti
    45.50
    anti
    42.00
    抗
    37.00
     ant
    36.75
    ANTI
    35.00
     Ant
    33.25
     анти
    32.75
    Activations Density 0.157%

    No Known Activations