© 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. 25822
    Prev
    Next
    INDEX
    Explanations

    IP address and authorization

    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
    æŃ£å¼ıä¸Ĭå¸Ĥ
    -0.08
    èĭ¦æ¶©
    -0.07
    éĹŃä¸Ĭçľ¼çĿĽ
    -0.07
    çĽ²äºº
    -0.07
    ä¿Ŀå¯Ĩ
    -0.07
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.07
    audi
    -0.07
    rypto
    -0.07
     Pratt
    -0.07
    åIJ¬æĩĤ
    -0.07
    POSITIVE LOGITS
     spoof
    0.09
    é»ijåIJįåįķ
    0.08
     legitimate
    0.08
    æģ¶æĦı
    0.08
     whit
    0.08
     whitelist
    0.08
    itimate
    0.08
     incoming
    0.08
     imperson
    0.08
     suspicious
    0.07
    Activations Density 0.148%

    No Known Activations