© 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. 24293
    Prev
    Next
    INDEX
    Explanations

    input

    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
    Äįina
    -0.08
     Jennings
    -0.07
    ä¸įä»İ
    -0.07
    á»Ļi
    -0.07
    éĩij鸡
    -0.06
    ä¸İ伦
    -0.06
    Äįin
    -0.06
    Dyn
    -0.06
    åĬªåĬĽ
    -0.06
    度çļĦ
    -0.06
    POSITIVE LOGITS
    æĨİ
    0.08
    ooth
    0.08
     berupa
    0.07
    irth
    0.07
    ritos
    0.07
    empa
    0.07
    _singleton
    0.07
    æī«æııäºĮç»´çłģ
    0.07
    _PB
    0.07
    ÃģP
    0.07
    Activations Density 0.004%

    No Known Activations