© 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. 1793
    Prev
    Next
    INDEX
    Explanations

    [foot] => [foot]

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

    No Comments

    Negative Logits
    脚
    -42.50
     foot
    -41.00
    Foot
    -37.75
     Foot
    -37.50
    腳
    -37.00
     FOOT
    -33.25
    -foot
    -32.50
    foot
    -32.50
    双脚
    -31.88
    _foot
    -31.00
    POSITIVE LOGITS
    rylic
    15.31
    琅
    15.25
    Tokenizer
    14.69
     Symphony
    14.69
    awai
    14.56
     Milwaukee
    14.50
     Tokyo
    14.44
    rin
    14.38
    material
    14.31
    ryn
    14.31
    Activations Density 0.154%

    No Known Activations