© 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. 19384
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    ousel
    -0.09
    à¸Ĭีà¸ŀ
    -0.09
    Īĺ
    -0.08
    æĿ¥å¾ĹåıĬ
    -0.08
    zehn
    -0.08
    надÑĨаÑĤÑĮ
    -0.08
    brigen
    -0.08
    èĪ¬åľ°
    -0.07
    soever
    -0.07
    zelfde
    -0.07
    POSITIVE LOGITS
    иÑĢов
    0.08
    lehr
    0.08
    asarkan
    0.08
    cratch
    0.07
    etti
    0.07
    s
    0.07
    лиз
    0.07
    cling
    0.07
    ungan
    0.07
    aging
    0.07
    Activations Density 0.080%

    No Known Activations