© 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. 29095
    Prev
    Next
    INDEX
    Explanations

    authentication and recognition systems

    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
    -ci
    -0.08
    unya
    -0.07
    ÙĪاØŃ
    -0.07
    éľ²æ°´
    -0.06
    çĦī
    -0.06
     latter
    -0.06
    mare
    -0.06
     Ëĩ
    -0.06
    马éŀį
    -0.06
    æł¼çļĦ
    -0.06
    POSITIVE LOGITS
    acos
    0.09
    ait
    0.07
    agio
    0.07
     appunto
    0.07
    åĩĮ
    0.07
    .codes
    0.07
    isz
    0.07
    ecie
    0.07
    inx
    0.06
    é¡»åľ¨
    0.06
    Activations Density 0.181%

    No Known Activations