© 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. 29347
    Prev
    Next
    INDEX
    Explanations

    .pone

    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
    èĢĮä¸Ķæľī
    -0.08
    engel
    -0.07
    maid
    -0.07
    æĥ³åĪ°
    -0.06
    гона
    -0.06
    éģ½
    -0.06
    åIJİ天
    -0.06
    arin
    -0.06
    ftware
    -0.06
    åıį
    -0.06
    POSITIVE LOGITS
    ãĥ¬ãĥ³ãĥģ
    0.08
    æłĩåĩĨä¿¡æģ¯
    0.08
    大èį¯æĪ¿
    0.07
    oghi
    0.07
    æľ¬é¢ĺåĪĨæŀIJ
    0.07
    åķĨæłĩä¿¡æģ¯
    0.07
    _FATAL
    0.07
    ç«Ļç«Ļ
    0.07
    omat
    0.07
    ichi
    0.07
    Activations Density 0.087%

    No Known Activations