© 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. 11150
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    åı¯æľĽ
    -0.07
    צ׾
    -0.07
    èĭĩ
    -0.07
    cid
    -0.07
    prs
    -0.07
    ç½
    -0.07
    ä»ĸ身ä¸Ĭ
    -0.07
    onen
    -0.07
     दà¥ĩà¤ĸ
    -0.07
     dÃłnh
    -0.07
    POSITIVE LOGITS
     name
    0.18
     names
    0.17
    åIJįåŃĹ
    0.17
    åIJį称
    0.16
    name
    0.15
    -name
    0.14
    _name
    0.13
     Name
    0.13
     Names
    0.13
    /name
    0.13
    Activations Density 0.184%

    No Known Activations