© 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. 56498
    Prev
    Next
    INDEX
    Explanations

    tail end of distributions

    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
    fullscreen
    -0.08
    åIJŀåIJIJ
    -0.07
    ihan
    -0.07
    اث
    -0.07
     Bea
    -0.07
    è·¯ç«Ļ
    -0.07
    æ²»
    -0.06
    æ°ı
    -0.06
     ÑĤеÑĢÑĢиÑĤоÑĢи
    -0.06
     avanti
    -0.06
    POSITIVE LOGITS
    å°¾éĥ¨
    0.11
     outliers
    0.10
     tails
    0.10
    Tail
    0.09
     tail
    0.09
    tail
    0.09
     Tail
    0.09
     Äijuôi
    0.08
    åĪ°ä½İ
    0.08
    /ext
    0.08
    Activations Density 0.033%

    No Known Activations