© 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. 14424
    Prev
    Next
    INDEX
    Explanations

    say Trump

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

    No Comments

    Negative Logits
    cache
    -20.38
    /cache
    -20.25
    _family
    -19.63
     cache
    -19.50
    Pictures
    -18.88
     searchData
    -18.75
    _cache
    -18.63
     caches
    -18.63
    erge
    -18.38
    父子
    -18.38
    POSITIVE LOGITS
     Trump
    21.25
    特朗普
    18.50
    Trump
    18.00
     Bannon
    14.13
    -Trump
    12.69
     tweeting
    12.63
    COVID
    12.56
    拜登
    12.31
     Donald
    12.13
     Indigenous
    11.50
    Activations Density 0.078%

    No Known Activations