© 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. 24433
    Prev
    Next
    INDEX
    Explanations

    contemplation, Arctostaphylos, arctoides, Arctiinae

    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
    erci
    -0.08
    çİ·
    -0.08
    isable
    -0.07
     вдо
    -0.07
    raries
    -0.07
    havn
    -0.07
    ibaldi
    -0.07
    ä¸įåłª
    -0.07
    ä¸Ĭ岸
    -0.07
    IFICATION
    -0.07
    POSITIVE LOGITS
    ë¡Ŀ
    0.09
    nowled
    0.07
    appa
    0.07
    éĩij森
    0.07
    ãĥĥãĤ¯
    0.07
    nowledge
    0.07
    inkel
    0.07
    å¤ķ
    0.07
    ron
    0.07
    itol
    0.07
    Activations Density 0.001%

    No Known Activations