© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 798
    Prev
    Next
    INDEX
    Explanations

    say cat

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

    No Comments

    Negative Logits
    滏
    -23.88
     Palestinian
    -22.63
    冀
    -20.75
    洺
    -20.63
    荚
    -19.88
    Penn
    -19.50
     soy
    -19.50
    EFR
    -19.25
     DF
    -18.88
    洸
    -18.88
    POSITIVE LOGITS
     CAT
    36.00
     cats
    36.00
     cat
    35.50
    CAT
    35.25
    猫
    33.25
    猫咪
    33.00
    cat
    32.50
     Cats
    31.75
    .cat
    31.63
    貓
    31.50
    Activations Density 0.114%

    No Known Activations