© 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. 32155
    Prev
    Next
    INDEX
    Explanations

    function definition

    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
    ngle
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.07
    ulut
    -0.07
    å±ķ示åĩº
    -0.07
     afar
    -0.07
     ChÃŃ
    -0.07
    å±ķå¼Ģåħ¨éĥ¨
    -0.07
    arella
    -0.07
    å°ĶèĴĻ
    -0.07
    PLE
    -0.07
    POSITIVE LOGITS
    ining
    0.08
    “
    0.06
    ed
    0.06
    eway
    0.06
    unction
    0.06
     yours
    0.06
    oya
    0.06
    lab
    0.06
    P
    0.06
    poke
    0.06
    Activations Density 0.228%

    No Known Activations