© 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. 9664
    Prev
    Next
    INDEX
    Explanations

    object response, spine, anemia

    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
    ä¸įè¡°
    -0.07
    è¾Ī
    -0.06
    —"
    -0.06
    mc
    -0.06
     deb
    -0.06
    arg
    -0.06
     prer
    -0.06
    —and
    -0.06
     Schedule
    -0.06
    éĸ²
    -0.06
    POSITIVE LOGITS
    resp
    0.09
    ä¹Łå¥½
    0.09
     vs
    0.09
    ä¹Łç½¢
    0.08
    ãģĦãģŁãĤĬ
    0.08
     versus
    0.08
    itivi
    0.08
    åŀĭåĴĮ
    0.08
    kah
    0.07
    izm
    0.07
    Activations Density 0.029%

    No Known Activations