© 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. 57524
    Prev
    Next
    INDEX
    Explanations

    technical terms or tools

    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
    è½¼
    -0.08
    unders
    -0.08
    iever
    -0.07
    ocrates
    -0.07
    erti
    -0.07
    edd
    -0.07
    iek
    -0.07
    ierto
    -0.07
    odb
    -0.07
    imed
    -0.07
    POSITIVE LOGITS
    åıªèĥ½è¯´
    0.07
    _logical
    0.07
    åıªæĺ¯ä¸Ģç§į
    0.07
    ä¸İä»ĸ
    0.06
    çļ®
    0.06
    æŃ£å¤§
    0.06
    è¿Ļæĸ¹éĿ¢çļĦ
    0.06
    .tell
    0.06
    yss
    0.06
    è°±
    0.06
    Activations Density 0.042%

    No Known Activations