© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43302
    Prev
    Next
    INDEX
    Explanations

    legal case citations and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大éĻ¢
    -0.07
    /cgi
    -0.07
    ç§ģæľį
    -0.06
    ÏģÏħ
    -0.06
    uple
    -0.06
    otto
    -0.06
    ob
    -0.06
     жÑĭ
    -0.06
    åĵŃ
    -0.06
    Unit
    -0.06
    POSITIVE LOGITS
    fels
    0.08
    elled
    0.07
    ónico
    0.07
    สà¸ļ
    0.07
     Nett
    0.07
    rear
    0.07
    éĢĨ天
    0.07
     advocate
    0.07
     Advocate
    0.07
    度
    0.07
    Activations Density 0.087%

    No Known Activations