© 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. 27585
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    หว
    -0.10
    ÙħÙĴ
    -0.10
    _FIELDS
    -0.09
    _REQ
    -0.09
    _FAIL
    -0.09
    à¹īà¸Ńย
    -0.09
    мп
    -0.08
    à¹Ģà¸ŀà¸Ĭร
    -0.08
    ÙĥÙıÙħÙĴ
    -0.08
    ä¼ģä¸ļåıĬ
    -0.08
    POSITIVE LOGITS
    ูà¸ģ
    0.09
    ï¾Ł
    0.09
    Ùİر
    0.08
    æµ·ä¸ľ
    0.08
     Vân
    0.07
    à¹Īวà¸ĩ
    0.07
    æ´Ľå¤«
    0.07
    ลูà¸ģ
    0.07
    สà¸Ķ
    0.07
    amore
    0.07
    Activations Density 2.104%

    No Known Activations