© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    [科学] => [科学]

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

    No Comments

    Negative Logits
    科学
    -72.50
     scientific
    -66.50
    科學
    -65.00
     science
    -63.75
     Science
    -59.00
     Scientific
    -59.00
    Scient
    -58.00
    scientific
    -57.75
    Science
    -56.00
    science
    -55.75
    POSITIVE LOGITS
    enen
    14.63
    iid
    13.50
    halb
    13.25
     Neue
    12.94
     LEDs
    12.88
     LP
    12.81
    LP
    12.44
    EEE
    12.31
    itar
    12.19
    (LP
    12.13
    Activations Density 0.357%

    No Known Activations