© 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. 64264
    Prev
    Next
    INDEX
    Explanations

    scientific notation or chemical formulas

    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
    zis
    -0.07
    æ¯Ľ
    -0.07
    dek
    -0.07
    imax
    -0.07
    habi
    -0.07
    ç»ĦæĪIJåijĺ
    -0.07
    irn
    -0.07
    ä¸Ĭæ·»
    -0.07
    çľī
    -0.07
    essed
    -0.07
    POSITIVE LOGITS
    åŁĤ
    0.07
    ä¸įå·®
    0.07
    (para
    0.07
    ç»ıèIJ¥çIJĨ念
    0.07
    ahan
    0.06
    è¿Ļæł·åŃIJ
    0.06
     appunto
    0.06
    خص
    0.06
    teroid
    0.06
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.06
    Activations Density 0.001%

    No Known Activations