© 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. 4194
    Prev
    Next
    INDEX
    Explanations

    ISBN

    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
    èij±èij±
    -0.08
     encar
    -0.07
    èĥŃ
    -0.07
    汪æ´ĭ
    -0.07
    åIJ¬éŁ³ä¹IJ
    -0.07
     Disqus
    -0.07
    æīĢåľ¨çļĦ
    -0.06
    icur
    -0.06
    æīĢåľ¨
    -0.06
    @[
    -0.06
    POSITIVE LOGITS
    rza
    0.07
    ÛķÙĪÛķ
    0.07
     nhau
    0.07
     Americas
    0.07
    ahlung
    0.06
    ç«Ļä¸Ĭ
    0.06
    cac
    0.06
    éĩijå®Ŀ
    0.06
    als
    0.06
    ates
    0.06
    Activations Density 0.026%

    No Known Activations