© 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. 45090
    Prev
    Next
    INDEX
    Explanations

    previous, legacy, successor

    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
    çľĭä¸Ģçľ¼
    -0.07
    iÄį
    -0.07
    å¾Īæĸ¹ä¾¿
    -0.07
    ajang
    -0.07
    æľĪçĶŁ
    -0.07
    éĥ½åĥı
    -0.07
    emps
    -0.07
    ä¹Łåıªæľī
    -0.07
    Grid
    -0.07
    æķ´ä¸ªä¸ĸçķĮ
    -0.07
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.19
    åİŁæľī
    0.18
    åİŁæĿ¥çļĦ
    0.15
     пÑĢеж
    0.14
    æŧçļĦ
    0.13
     previous
    0.13
    æŧ
    0.13
     bisherigen
    0.13
     existing
    0.13
     previously
    0.13
    Activations Density 0.508%

    No Known Activations