© 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. 9575
    Prev
    Next
    INDEX
    Explanations

    pass on, transmit, passage, inheritance

    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
    RITE
    -0.07
    isposable
    -0.07
    иÑģÑĤо
    -0.07
    æĿ¥ä¿¡
    -0.07
    URI
    -0.07
    ardu
    -0.07
    Ä±ÅŁtır
    -0.07
    æıIJåįĩèĩªå·±
    -0.07
    oÅĤ
    -0.07
    incon
    -0.07
    POSITIVE LOGITS
    ä¼łåĪ°
    0.14
    ä¼łéĢĴ
    0.13
    ä¼łå¯¼
    0.12
    ä¼łéĢĴç»Ļ
    0.12
    ä¼ł
    0.12
    ä¼łç»Ļ
    0.12
    ä¼ĿãĤı
    0.11
     across
    0.11
     transmission
    0.11
     пеÑĢедаÑĩе
    0.11
    Activations Density 0.109%

    No Known Activations