© 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. 31200
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
    ilden
    -0.09
    æĿ¥è¶Ĭ
    -0.09
     Magnum
    -0.08
    issen
    -0.08
     existi
    -0.08
    авли
    -0.08
    ÑĥÑīе
    -0.07
    çĭ¬è¡Į
    -0.07
    abel
    -0.07
     enx
    -0.07
    POSITIVE LOGITS
    OA
    0.07
    å§Ĩæĸ¯
    0.07
    lat
    0.06
    æ²®
    0.06
    âĪ
    0.06
     subordinate
    0.06
    IP
    0.06
    ä¸įå±ŀäºİ
    0.06
     bund
    0.06
    åľ¨ä¸Ģ个
    0.06
    Activations Density 0.009%

    No Known Activations