© 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. 47932
    Prev
    Next
    INDEX
    Explanations

    citations and bibliographies

    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
     láºŃp
    -0.08
    øn
    -0.07
    nee
    -0.07
    irie
    -0.07
    дÑĥм
    -0.07
    izo
    -0.06
    ä»Ķ
    -0.06
    .ibm
    -0.06
     epis
    -0.06
    ivo
    -0.06
    POSITIVE LOGITS
    opat
    0.08
     **.**
    0.08
    ilha
    0.07
    åĸĿçĿĢ
    0.07
    éģĵ人
    0.07
    ellement
    0.07
    ä¸½å¨ľ
    0.07
    kontak
    0.07
    æ³½æ°ij
    0.07
     Parch
    0.07
    Activations Density 0.217%

    No Known Activations