© 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. 8507
    Prev
    Next
    INDEX
    Explanations

    repeating sequences of numbers or words

    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
    èݱ德
    -0.09
    Bron
    -0.07
     Bron
    -0.07
    æĸŁéħĮ
    -0.07
    åIJĥéĨĭ
    -0.07
    kdir
    -0.07
    ĵĺ
    -0.07
    ügy
    -0.07
    fork
    -0.07
    è¡¡éĩı
    -0.07
    POSITIVE LOGITS
     repeating
    0.09
     periodic
    0.09
    循
    0.08
    å°ıæķ°
    0.07
    ä¸įéĹ´æĸŃ
    0.07
    digits
    0.07
    åij¨æľŁæĢ§
    0.07
     alternating
    0.07
     decimals
    0.07
     decimal
    0.07
    Activations Density 0.007%

    No Known Activations