© 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. 1848
    Prev
    Next
    INDEX
    Explanations

    星

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

    No Comments

    Negative Logits
     stars
    -38.00
    星
    -35.50
     star
    -34.75
     Stars
    -34.75
    Stars
    -33.50
    Star
    -32.75
    星星
    -32.50
    stars
    -31.88
     Star
    -31.63
    -stars
    -31.38
    POSITIVE LOGITS
     Documentary
    14.88
     الرياض
    14.63
    anian
    14.25
     ethical
    14.13
    EM
    13.69
    我院
    13.69
    .JSON
    13.63
    院
    13.56
     EM
    13.38
     EMC
    13.19
    Activations Density 0.098%

    No Known Activations