© 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. 23077
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and symbols

    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
    å¿«åĪ°
    -0.06
    [].
    -0.06
    que
    -0.06
    çīĽ
    -0.06
     spit
    -0.06
    ier
    -0.06
    áĢĻáĢ¼
    -0.06
    ling
    -0.06
    ØŃد
    -0.06
    TL
    -0.06
    POSITIVE LOGITS
     Jonas
    0.07
    微信æī«ä¸Ģæī«
    0.07
     widest
    0.07
    ä½ľåĪĻ
    0.07
    keit
    0.07
     besteh
    0.07
    å·´å¡ŀ
    0.07
    irts
    0.06
    çĤ¹åĩ»åĽ¾çīĩ
    0.06
    udit
    0.06
    Activations Density 0.006%

    No Known Activations