© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59920
    Prev
    Next
    INDEX
    Explanations

    or will be

    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
    Negative Logits
     Sole
    -0.08
    iles
    -0.08
    nie
    -0.08
    çĶ¨çĶµ
    -0.07
    缺氧
    -0.07
    sole
    -0.07
    论
    -0.07
    à¤ķà¥įषण
    -0.07
    åį´è¿ĺæĺ¯
    -0.06
    ead
    -0.06
    POSITIVE LOGITS
    èĴ¸
    0.07
    çŁ¥ä¹ĭ
    0.07
    atory
    0.07
    quivo
    0.07
    otto
    0.07
    adius
    0.07
     Steele
    0.07
    ائد
    0.07
    tral
    0.06
    æł¹æľ¬å°±ä¸į
    0.06
    Activations Density 0.110%

    No Known Activations