© 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. 61764
    Prev
    Next
    INDEX
    Explanations

    phenotypic

    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
    åĵ¡
    -0.09
    ness
    -0.09
    iders
    -0.08
    åijĺ
    -0.07
    iates
    -0.07
    anza
    -0.07
    ëĦĪ
    -0.07
    heed
    -0.07
    HING
    -0.07
    icales
    -0.07
    POSITIVE LOGITS
    åĴĮè¡Į为
    0.09
    keen
    0.08
    ovÄĽ
    0.08
    irma
    0.07
    adata
    0.07
     OWNER
    0.07
    éric
    0.07
    à¸ļัà¸ķิ
    0.07
    ize
    0.07
    /gen
    0.07
    Activations Density 0.018%

    No Known Activations