© 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. 27781
    Prev
    Next
    INDEX
    Explanations

    Reveals new ballistic missile, grip strength, festival

    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
    ç«ĻåĨħæIJľç´¢
    -0.08
    è¿ĻäºĽåĽłç´ł
    -0.08
    èĤºèħij
    -0.08
    [âĢ¦
    -0.07
    éĩĬ
    -0.07
    年建
    -0.07
    kees
    -0.07
    æ¯ıä¸Ģ份
    -0.07
    ersist
    -0.07
    çıĬ
    -0.07
    POSITIVE LOGITS
    _eof
    0.08
    çŃīä»·
    0.07
    uler
    0.07
    .eof
    0.07
    timo
    0.07
    æĹłç©·
    0.07
    天çİĭ
    0.07
     caval
    0.07
     panoramic
    0.06
     Comple
    0.06
    Activations Density 0.003%

    No Known Activations