© 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. 11571
    Prev
    Next
    INDEX
    Explanations

    mathematical/programming symbols

    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
    hart
    -0.07
    heart
    -0.07
    ¨
    -0.07
    çļĦæĺ¯ä¸Ģ个
    -0.07
    )<<
    -0.06
    o
    -0.06
    æ©Ł
    -0.06
    åħĨ
    -0.06
    .$.
    -0.06
    å¾·åįİ
    -0.06
    POSITIVE LOGITS
    leven
    0.07
     Inde
    0.07
    rior
    0.07
    ë¦Ħ
    0.06
    çĶļ
    0.06
    ç½Ĺåħ°
    0.06
    ühren
    0.06
    elaide
    0.06
    为èį£
    0.06
    ibase
    0.06
    Activations Density 0.007%

    No Known Activations