© 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. 45829
    Prev
    Next
    INDEX
    Explanations

    part of a structure or word

    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
    ä¸Ģç³»åĪĹ
    -0.06
    uri
    -0.06
    åħĪåIJİ
    -0.06
    éĽĨåĽ¢æľīéĻIJ责任åħ¬åı¸
    -0.06
    æľ¬äººåľ¨
    -0.06
    æķĻäºİ
    -0.06
    ç®Ĺä¸įä¸Ĭ
    -0.06
    kits
    -0.06
    оÑĤно
    -0.06
    à¸ģำ
    -0.06
    POSITIVE LOGITS
     portion
    0.18
     part
    0.16
     portions
    0.16
     version
    0.15
    éĥ¨åĪĨæĺ¯
    0.15
    éĥ¨åĪĨ
    0.15
    éĥ¨ä»½
    0.15
     versions
    0.14
    çīĪ
    0.14
    çīĪæľ¬
    0.14
    Activations Density 0.147%

    No Known Activations