© 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. 19938
    Prev
    Next
    INDEX
    Explanations

    limitations of

    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
    ucch
    -0.07
    Öģ
    -0.07
    -svg
    -0.07
    à¸Ĺัà¸ŀ
    -0.06
    èĽ¹
    -0.06
    ellini
    -0.06
    å¾·åŁº
    -0.06
    ìĩĦ
    -0.06
    egue
    -0.06
    åıĮ羸
    -0.06
    POSITIVE LOGITS
    æĻī
    0.07
    è¿ĻäºĭåĦ¿
    0.07
     Dank
    0.07
    å©¿
    0.07
    anton
    0.06
    osc
    0.06
     Donovan
    0.06
    åį¿
    0.06
    è¿ŀäºij
    0.06
    并ä¸į代表
    0.06
    Activations Density 0.079%

    No Known Activations