© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61834
    Prev
    Next
    INDEX
    Explanations

    mathematical limits or pandas indexing

    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
    maa
    -0.07
    kini
    -0.07
    à¶Ńà·Ķ
    -0.07
    jay
    -0.07
    ķĮ
    -0.07
    æĮīæŶå®ĮæĪIJ
    -0.07
    åľ¨ç»Ļ
    -0.06
    ãģĨãģ¡ãģ«
    -0.06
    æĮīæľĪ
    -0.06
    \Id
    -0.06
    POSITIVE LOGITS
     Ãļl
    0.08
    ä¹İ
    0.08
    ÏĨή
    0.07
    aker
    0.07
    _{
    0.07
    ajar
    0.07
    oscope
    0.07
    ikov
    0.07
    æĸ¼
    0.07
    æĪĸåĪ©çĶ¨
    0.07
    Activations Density 0.002%

    No Known Activations