© 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. 61221
    Prev
    Next
    INDEX
    Explanations

    fungus, parasite, species, larvae, plants, medicine, nematodes, adenocarcinoma

    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
    ims
    -0.07
    iman
    -0.07
    ListOf
    -0.07
    èĥ¡ä¹±
    -0.06
    æķ´å¥Ĺ
    -0.06
    åIJĦè¡Į
    -0.06
    ola
    -0.06
    ilas
    -0.06
    俱åħ¨
    -0.06
    ä¹ı
    -0.06
    POSITIVE LOGITS
     danh
    0.08
    ä¹ĭæĺŁ
    0.08
    Âł
    0.07
    antum
    0.07
    0.07
     sibling
    0.07
     Pregun
    0.07
     sekaligus
    0.07
    riendly
    0.07
     bü
    0.07
    Activations Density 0.119%

    No Known Activations