© 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. 19107
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    aler
    -0.07
    zi
    -0.07
    ushi
    -0.07
    parator
    -0.06
    åĴĮå·¥ä½ľ
    -0.06
    åijĹ
    -0.06
    ¨
    -0.06
    uffer
    -0.06
    unto
    -0.06
    une
    -0.06
    POSITIVE LOGITS
    ä¸ĢæľĿ
    0.09
    usercontent
    0.08
    ÑĥÑĤа
    0.08
    ä¸½å¨ľ
    0.07
    ÑĥÑĤÑĮ
    0.07
    adh
    0.07
    aturas
    0.07
    кÑĢи
    0.07
    ли
    0.07
    ç«£
    0.07
    Activations Density 0.055%

    No Known Activations