© 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. 60700
    Prev
    Next
    INDEX
    Explanations

    Product Design

    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
    пле
    -0.06
    åĬ¨äº§
    -0.06
    ÄįiÄĩ
    -0.06
    пиÑģа
    -0.06
    _tol
    -0.06
    çĭł
    -0.06
    èıł
    -0.06
    åı¯æĺ¯ä¸Ģ
    -0.06
     باش
    -0.06
    _ele
    -0.06
    POSITIVE LOGITS
    /Home
    0.09
    /Public
    0.08
    /public
    0.08
    /Y
    0.07
    um
    0.07
    /angular
    0.07
    /internal
    0.07
    /main
    0.07
     ones
    0.07
    /V
    0.07
    Activations Density 0.524%

    No Known Activations