© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    before or after

    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
    _INFO
    -0.07
    _ordered
    -0.07
     drains
    -0.07
    æłĩåĩĨä¿¡æģ¯
    -0.06
    /info
    -0.06
     sheds
    -0.06
    à´¨àµįà´¨
    -0.06
    éĻĨç»Ń
    -0.06
    æħµ
    -0.06
    arvi
    -0.06
    POSITIVE LOGITS
    æĭ¬
    0.09
     curly
    0.08
    isky
    0.08
    è²ī
    0.08
     ÙĪÙĤبÙĦ
    0.07
    лÑĮкÑĥ
    0.07
    羡
    0.07
    ffffffff
    0.07
    对æķ´ä¸ª
    0.07
    宾è¯Ń
    0.07
    Activations Density 0.044%

    No Known Activations