© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17743
    Prev
    Next
    INDEX
    Explanations

    ormocer-based composites

    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
    åħįè´¹åľ¨çº¿
    -0.07
    åĪ«åĨį
    -0.07
    à¸Ńà¸ĩ
    -0.07
    ÄĻż
    -0.07
    Ïĥια
    -0.07
    /pm
    -0.07
    лайн
    -0.07
    æī£
    -0.07
    æĶ¿æ²»å»ºè®¾
    -0.06
     Hurt
    -0.06
    POSITIVE LOGITS
    doch
    0.07
    ÑĮ
    0.06
    以åıĬ对
    0.06
    ashes
    0.06
    ç¿°
    0.06
    èĭ¥å¹²
    0.06
    æĽ¾ç»ı
    0.06
    æµģãĤĮ
    0.06
    彤
    0.06
    aix
    0.06
    Activations Density 0.250%

    No Known Activations