© 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. 1620
    Prev
    Next
    INDEX
    Explanations

    [forest] => [trees]

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

    No Comments

    Negative Logits
    森林
    -40.00
     Forest
    -38.75
     forests
    -38.50
     forest
    -38.25
    forest
    -34.00
    Forest
    -33.00
    林
    -30.75
    林业
    -27.88
    树林
    -26.25
     forestry
    -25.50
    POSITIVE LOGITS
     math
    16.00
    PhoneNumber
    15.94
     engagement
    15.94
    Math
    15.88
     Math
    15.88
    Eng
    15.50
     THC
    15.44
     Engagement
    15.25
     mathematic
    15.06
    ゃ
    15.00
    Activations Density 0.102%

    No Known Activations