© 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. 10481
    Prev
    Next
    INDEX
    Explanations

    you can

    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
    家家æĪ·æĪ·
    -0.08
    à¸Ńà¸Ķ
    -0.08
    вики
    -0.07
    agem
    -0.07
    horia
    -0.07
    第ä¸Ģ人æ°ijåĮ»éĻ¢
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    .Scope
    -0.07
     sej
    -0.07
    ØŃØ©
    -0.07
    POSITIVE LOGITS
    æľ¬çīĪ
    0.08
    opo
    0.08
    ĥģ
    0.07
    éĽĨåĽ¢åħ¬åı¸
    0.07
     Hatch
    0.07
    oke
    0.06
    egin
    0.06
    å½·
    0.06
    itzer
    0.06
    屿
    0.06
    Activations Density 0.004%

    No Known Activations