© 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. 2019
    Prev
    Next
    INDEX
    Explanations

    apple

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

    No Comments

    Negative Logits
    苹果
    -54.25
    apple
    -52.50
    Apple
    -52.50
     Apple
    -52.50
     apple
    -52.00
    /apple
    -47.50
    .apple
    -44.25
     apples
    -44.00
     APPLE
    -42.25
    APPLE
    -41.50
    POSITIVE LOGITS
    burn
    16.00
    Burn
    15.56
     burn
    15.44
     Venezuela
    15.25
     burning
    14.75
     Burn
    14.63
    河道
    14.44
     MYSQL
    14.38
     Garc
    14.25
    ischer
    14.25
    Activations Density 0.151%

    No Known Activations