© 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. 41334
    Prev
    Next
    INDEX
    Explanations

    generic type with extends

    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
    egram
    -0.08
    /OR
    -0.07
    atives
    -0.07
    /display
    -0.07
    ATIVE
    -0.07
    .ua
    -0.07
    ä¸įæĹ©
    -0.06
    ên
    -0.06
    çļĦç¡®
    -0.06
    icients
    -0.06
    POSITIVE LOGITS
    _traits
    0.07
    红æŀ£
    0.07
    -generic
    0.07
    à²Ĥà²Ĺ
    0.07
    peek
    0.07
     uitge
    0.07
    ɵ
    0.06
    имо
    0.06
    enz
    0.06
    contra
    0.06
    Activations Density 0.055%

    No Known Activations