© 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. 40455
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals and derivatives

    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
    quita
    -0.08
    äºijä¸Ń
    -0.08
    ienne
    -0.08
    窮
    -0.08
    поÑĤе
    -0.07
    ç©·
    -0.07
    leve
    -0.07
     judici
    -0.07
    ಿà²ķ
    -0.07
    igio
    -0.07
    POSITIVE LOGITS
    onio
    0.07
    éĤ£ä¸įæĺ¯
    0.07
    ç»ĵæŀľæĺ¯
    0.07
    åѦå¾Ĺ
    0.07
    å°ĨæĮģç»Ń
    0.06
    å½ķå¾Ĺ
    0.06
    çĢ¬
    0.06
    irs
    0.06
    -eyed
    0.06
     Pl
    0.06
    Activations Density 0.003%

    No Known Activations