© 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. 32833
    Prev
    Next
    INDEX
    Explanations

    names of people, things, or solutions

    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
    æł¹æľ¬å°±æ²¡æľī
    -0.07
     ìĿ´ê²Į
    -0.06
    äºĭ件ä¸Ń
    -0.06
    yttä
    -0.06
    à¥ĭर
    -0.06
    çĿ¹
    -0.06
    lava
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    illum
    -0.06
     Vaughan
    -0.06
    POSITIVE LOGITS
     nor
    0.09
    èĢĮæĺ¯è¦ģ
    0.08
    ä½Ĩåı¯ä»¥
    0.08
    èĢĮæĺ¯
    0.07
    _abstract
    0.07
     Nor
    0.07
     sondern
    0.07
    ieten
    0.07
    ä½įçļĦ
    0.07
    èĢĮæĺ¯åľ¨
    0.07
    Activations Density 0.049%

    No Known Activations