© 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. 12614
    Prev
    Next
    INDEX
    Explanations

    movie genre film

    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
    lessness
    -0.07
    ãģ®ãģĵãģ¨
    -0.06
    -Bold
    -0.06
    端
    -0.06
    代表çļĦ
    -0.06
    vai
    -0.06
    éĿŀçī©è´¨
    -0.06
    лоÑģÑĤÑĮ
    -0.06
    endu
    -0.06
    .store
    -0.06
    POSITIVE LOGITS
     genre
    0.11
    ç±»çļĦ
    0.11
    ç±»
    0.11
    ç±»åĴĮ
    0.11
    ç±»çŃī
    0.09
     жан
    0.09
    ä¸Ń带
    0.08
    ceph
    0.08
    é¡ŀçļĦ
    0.08
    ä½ĵè£ģ
    0.08
    Activations Density 0.272%

    No Known Activations