© 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. 21345
    Prev
    Next
    INDEX
    Explanations

    obvious noticeable

    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
    opan
    -0.10
    iform
    -0.09
    zysta
    -0.09
    anne
    -0.09
    åijĺçļĦ
    -0.08
    ../../../
    -0.08
    mlin
    -0.08
    à¦ģ
    -0.08
    ylland
    -0.08
     ÐŁÐ¾Ð¿ÑĢо
    -0.08
    POSITIVE LOGITS
    åľ°åIJij
    0.09
    ity
    0.08
    à¸Ĭัà¸Ķ
    0.08
    äºİä¸ĸ
    0.08
    åľ°å°Ĩ
    0.08
    çªģåĩºçļĦ
    0.07
    åľ°è¿Ľè¡Į
    0.07
    åľ°æĬĬ
    0.07
    åľ°åľ¨
    0.07
    "
    0.07
    Activations Density 0.029%

    No Known Activations