© 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. 22474
    Prev
    Next
    INDEX
    Explanations

    federal agencies or programming keywords

    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
    enf
    -0.07
    leit
    -0.07
    .Linked
    -0.07
    ļ
    -0.07
    ɵ
    -0.07
     reg
    -0.07
    stell
    -0.07
    rese
    -0.07
    اÙĨس
    -0.07
    ëĤĺìĿ´
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ichter
    0.07
    å´½
    0.07
    iertel
    0.07
     elsif
    0.06
     orchestrated
    0.06
    æģ¯
    0.06
    IfExists
    0.06
    баÑĢ
    0.06
    aylor
    0.06
    Activations Density 0.006%

    No Known Activations