© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46797
    Prev
    Next
    INDEX
    Explanations

    modelmiddleware, landscape, model, ing

    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
    bis
    -0.07
    ANGE
    -0.07
     bis
    -0.07
     pat
    -0.07
    angi
    -0.06
    pat
    -0.06
    ORTE
    -0.06
     адÑĢеÑģ
    -0.06
    å¿ĥæĦı
    -0.06
    ORTH
    -0.06
    POSITIVE LOGITS
    çļĦç«ŀäºī
    0.09
    ç«ŀäºī
    0.08
    .createComponent
    0.07
    åĬ¨éĿĻ
    0.07
    转载æĪĸ
    0.07
    .combine
    0.07
     competition
    0.07
    é«ĺç§ij
    0.07
     combined
    0.07
    competition
    0.07
    Activations Density 0.002%

    No Known Activations