© 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. 18281
    Prev
    Next
    INDEX
    Explanations

    etiologies and their mechanisms

    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
    æ¡Ī
    -0.08
    è¿ĺæľīä¸Ģç§į
    -0.08
    case
    -0.07
    éĢŁ
    -0.07
     Catania
    -0.07
    bjerg
    -0.06
     ARISING
    -0.06
    æ¡Īä¸Ń
    -0.06
     Walsh
    -0.06
    ãĥĥãĤ·ãĥ§ãĥ³
    -0.06
    POSITIVE LOGITS
     dabei
    0.08
     übrigens
    0.08
    ordu
    0.07
    éĢļ常为
    0.07
    ake
    0.07
     btw
    0.07
    otten
    0.06
    jeta
    0.06
    icole
    0.06
    ä½łçŁ¥éģĵåIJĹ
    0.06
    Activations Density 0.144%

    No Known Activations