© 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. 31842
    Prev
    Next
    INDEX
    Explanations

    What is the value of

    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
    è¦ģä¹Īæĺ¯
    -0.07
     either
    -0.07
    è¦ģä¹Ī
    -0.06
    utam
    -0.06
    åģ¿
    -0.06
    endah
    -0.06
    ä¸Ĭåľº
    -0.06
    ତି
    -0.06
    (es
    -0.06
    æĢ§ä»·æ¯Ķé«ĺ
    -0.06
    POSITIVE LOGITS
     berüh
    0.07
    inch
    0.07
    äºĨåIJ§
    0.07
    解æķ£
    0.07
    letters
    0.07
    Ùģا
    0.07
    eria
    0.06
    æĸ°æĿIJ
    0.06
     admin
    0.06
    æģª
    0.06
    Activations Density 0.190%

    No Known Activations