© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21558
    Prev
    Next
    INDEX
    Explanations

    purpose of, having various, adding them, evaluating overlap

    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
     olyan
    -0.07
    _catalog
    -0.07
    wth
    -0.06
     zwar
    -0.06
    жда
    -0.06
    对ä¸Ĭè¿°
    -0.06
    íķĺìĺĢìľ¼ë©°
    -0.06
     unnecessarily
    -0.06
    éģ¿åħįåĽł
    -0.06
     Garant
    -0.06
    POSITIVE LOGITS
    为ä¹ĭ
    0.08
    ä¸ĭåIJĮ
    0.08
    åĬłä»¥
    0.08
    боÑĢо
    0.08
    ارÙĩ
    0.07
    èĩ´çļĦ
    0.07
     etc
    0.07
    éĬŃ
    0.07
     appunto
    0.07
    ìĹŃ
    0.07
    Activations Density 0.251%

    No Known Activations