© 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. 1985
    Prev
    Next
    INDEX
    Explanations

    science

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

    No Comments

    Negative Logits
     science
    -21.13
    科技
    -19.00
    science
    -19.00
    酒
    -16.50
     Science
    -16.13
    树
    -16.00
    fire
    -15.69
     sea
    -15.69
     wine
    -15.63
    Science
    -15.44
    POSITIVE LOGITS
    .widget
    17.38
    ARNING
    17.13
    ismatic
    16.75
    驼
    16.50
     widgets
    16.50
    widget
    16.25
    (Symbol
    16.13
    widgets
    16.00
     Symbol
    15.94
    症状
    15.88
    Activations Density 0.233%

    No Known Activations