© 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. 33849
    Prev
    Next
    INDEX
    Explanations

    intersection and 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
    ä¸Ģç³»åĪĹ
    -0.07
     Nelson
    -0.07
    ulators
    -0.07
    åIJĦ项任åĬ¡
    -0.07
    èĢħä¼ĺåħĪ
    -0.07
    ulat
    -0.06
    ëĭ¨ìĿĦ
    -0.06
     ÏĦά
    -0.06
    номо
    -0.06
    cule
    -0.06
    POSITIVE LOGITS
    交éĽĨ
    0.12
    åħ±äº«
    0.11
    (shared
    0.10
    shared
    0.10
     shared
    0.10
    overlap
    0.10
    åħ±åIJĮçļĦ
    0.10
    éĩįåıł
    0.10
    Shared
    0.10
     overlap
    0.09
    Activations Density 0.014%

    No Known Activations