© 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. 62805
    Prev
    Next
    INDEX
    Explanations

    existence, possibility, or questions

    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
    ä¸Ģçľĭ
    -0.08
     Porr
    -0.07
    .GetData
    -0.07
    åİĨ
    -0.07
    arken
    -0.07
    è¿ľè¿ľçļĦ
    -0.06
     potenz
    -0.06
    elius
    -0.06
     whichever
    -0.06
    æľ¬çıŃ
    -0.06
    POSITIVE LOGITS
     exists
    0.17
     exist
    0.17
     existence
    0.16
    çļĦåŃĺåľ¨
    0.16
    åŃĺåľ¨
    0.16
    åŃĺåľ¨çļĦ
    0.16
    Exists
    0.16
    exists
    0.16
     Exists
    0.15
    æĺ¯åIJ¦åŃĺåľ¨
    0.15
    Activations Density 0.592%

    No Known Activations