© 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. 1809
    Prev
    Next
    INDEX
    Explanations

    receptor, property, networks, reflexology, floating point

    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
    çIJµ
    -0.07
    æµİ
    -0.06
    İ
    -0.06
    æĺİæĸĩ
    -0.06
    ostas
    -0.06
    illator
    -0.06
    åıªå¥½
    -0.06
    нга
    -0.06
    çļĦæľīæķĪ
    -0.06
    Ïģαι
    -0.06
    POSITIVE LOGITS
    åºĦéķĩ
    0.09
    å±±éķĩ
    0.07
    ä¹Łä¼ļå½±åĵį
    0.07
    eh
    0.07
    人åħ³æ³¨
    0.07
    ZW
    0.07
    erras
    0.07
    ÃŃculos
    0.07
    ä¸Ĭä¼łåĽ¾çīĩ
    0.07
    esson
    0.07
    Activations Density 0.288%

    No Known Activations