© 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. 61769
    Prev
    Next
    INDEX
    Explanations

    J.J

    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
    _stderr
    -0.08
    åIJŀåIJIJ
    -0.07
    ç»ıåıĹ
    -0.07
    æīĴ
    -0.07
    åħ·åIJĪ
    -0.07
    åİĭå®ŀ
    -0.07
    åİĭç´§
    -0.07
    /title
    -0.07
     particulares
    -0.06
    /sl
    -0.06
    POSITIVE LOGITS
    åİ»ä¸ĸ
    0.07
    æĮ¯
    0.07
     ÙĪابÙĨ
    0.07
     op
    0.07
    errupted
    0.07
    åİ»ä¸ĸäºĨ
    0.06
    ocate
    0.06
    caler
    0.06
    天å¤ĸ
    0.06
     ÐĵÐĺÐij
    0.06
    Activations Density 0.062%

    No Known Activations