© 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. 40795
    Prev
    Next
    INDEX
    Explanations

    function calls or parameters

    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
    庵
    -0.06
    ool
    -0.06
    é£
    -0.06
    ת
    -0.06
     Wilkinson
    -0.06
    使èĢħ
    -0.05
    åĻĤ
    -0.05
    æĪijå¿ĥ
    -0.05
    на
    -0.05
    ulpt
    -0.05
    POSITIVE LOGITS
    anh
    0.09
    åĬŀåıij
    0.08
    itkan
    0.08
    ossal
    0.08
    istin
    0.08
    åѦä¸ĵä¸ļ
    0.08
    afx
    0.08
    UserController
    0.08
    éĥ¨çº§
    0.08
    иÑģло
    0.08
    Activations Density 0.005%

    No Known Activations