© 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. 19604
    Prev
    Next
    INDEX
    Explanations

    forgot to check

    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
    å¦Ĥæŀľåı¯ä»¥
    -0.08
    oise
    -0.07
    ä¸į满æĦı
    -0.07
    ä¸įçIJĨæĥ³
    -0.07
    ä¸į太好
    -0.07
    agt
    -0.06
    åĻª
    -0.06
    artal
    -0.06
    Inform
    -0.06
    ankan
    -0.06
    POSITIVE LOGITS
     accidentally
    0.14
     mistake
    0.13
    å¿ĺãĤĮ
    0.12
    éģĹæ¼ı
    0.12
     inadvert
    0.12
     inadvertently
    0.12
     nhầm
    0.11
     mistakes
    0.11
    误
    0.11
    å¿ĺè®°
    0.11
    Activations Density 0.165%

    No Known Activations