© 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. 4082
    Prev
    Next
    INDEX
    Explanations

    from or to directions

    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
     merely
    -0.08
    ä»ħä»ħæĺ¯
    -0.07
    illes
    -0.07
    åıªæĺ¯ä¸Ģ
    -0.07
    añ
    -0.07
    LEMENT
    -0.07
    æĥ³è±¡
    -0.07
    è´±
    -0.07
    gow
    -0.07
     mere
    -0.07
    POSITIVE LOGITS
     Start
    0.08
    é«ĺå¯Ĩ
    0.07
    start
    0.07
     start
    0.07
    缴æĮĩ
    0.07
    å¼Ģå§ĭ
    0.07
    峪
    0.07
     langsung
    0.07
    ussions
    0.07
     boldly
    0.07
    Activations Density 0.010%

    No Known Activations