© 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. 34595
    Prev
    Next
    INDEX
    Explanations

    pi

    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
    ../../
    -0.09
    landet
    -0.08
    heiten
    -0.08
    heits
    -0.07
    amani
    -0.07
    ../../../
    -0.07
    à¸ķราย
    -0.07
    åIJĦ项
    -0.07
    ../../../../
    -0.07
    ansson
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.10
     electrons
    0.08
    »
    0.07
    duct
    0.07
    _erase
    0.07
    ä¸Ń游
    0.07
    -elect
    0.07
    ohl
    0.07
     CORR
    0.07
    bond
    0.06
    Activations Density 0.001%

    No Known Activations