© 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. 14543
    Prev
    Next
    INDEX
    Explanations

    say foods

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

    No Comments

    Negative Logits
    盐
    -18.63
    �
    -16.13
     salt
    -16.00
     fans
    -15.94
    �
    -15.94
    GBT
    -15.75
    *log
    -15.50
     Salt
    -15.50
    ellt
    -15.25
     gul
    -15.19
    POSITIVE LOGITS
    食物
    16.13
    的食物
    15.31
    (SIG
    14.25
    mic
    13.88
    plants
    13.56
     plants
    13.31
     foods
    13.25
    macros
    13.06
    diet
    13.00
    ve
    12.88
    Activations Density 0.097%

    No Known Activations