© 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. 1080
    Prev
    Next
    INDEX
    Explanations

    [edit] => [edit]

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

    No Comments

    Negative Logits
    编辑
    -39.25
     edit
    -38.50
     editor
    -37.50
     EDIT
    -37.00
    edit
    -37.00
     Editor
    -36.50
     editing
    -35.75
    Edit
    -35.50
    Editor
    -35.25
     editors
    -35.25
    POSITIVE LOGITS
    fuel
    17.00
     Fuel
    15.50
     fuel
    15.50
    燃料
    15.50
     Tank
    15.31
    ชา
    15.31
     Jes
    15.25
     username
    15.19
    姜
    15.19
    沛
    14.75
    Activations Density 0.113%

    No Known Activations