© 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. 8315
    Prev
    Next
    INDEX
    Explanations

    numbers in text

    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
    åħ¬ä¼ļ
    -0.08
    åħ¬æľĥ
    -0.07
    _TRANSL
    -0.07
    ÑĪка
    -0.07
    etas
    -0.07
     Cleveland
    -0.07
    edale
    -0.07
    лиÑģ
    -0.07
    ugin
    -0.07
    æīĢèĥ½
    -0.07
    POSITIVE LOGITS
    辩
    0.07
    teres
    0.07
    ibi
    0.06
    轨
    0.06
    ãĥ¼ãĥĬ
    0.06
    eret
    0.06
    uni
    0.06
    unn
    0.06
    Ñĥне
    0.06
    çijļ
    0.06
    Activations Density 0.001%

    No Known Activations