© 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. 22838
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and where clauses

    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
    åıĪä¸įèĥ½
    -0.07
    æķħèĢĮ
    -0.07
    ķĮ
    -0.07
    Ø´Ùĩ
    -0.07
    ãģłãģĭãĤīãģĵãģĿ
    -0.07
    оÑī
    -0.07
     jadi
    -0.07
    gens
    -0.07
    åĽłèĢĮ
    -0.07
    nitz
    -0.07
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.11
    æĦıæĢĿæĺ¯
    0.09
     where
    0.09
     wobei
    0.09
    where
    0.08
    åħ¶ä¸Ńæľī
    0.08
    ä¹Łå°±æĺ¯è¯´
    0.08
     meaning
    0.08
     où
    0.07
    λά
    0.07
    Activations Density 0.024%

    No Known Activations