© 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. 8312
    Prev
    Next
    INDEX
    Explanations

    quantities like million, crore, K, billions

    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
    æŃ£çĽ´
    -0.07
    odem
    -0.07
    inaire
    -0.07
    ä¸Ģè¡Į
    -0.06
    olygon
    -0.06
    ippi
    -0.06
    ofilm
    -0.06
    heiros
    -0.06
    æĿľé¹ĥ
    -0.06
    icola
    -0.06
    POSITIVE LOGITS
    åºŀ大
    0.09
    antin
    0.08
    ä¸ĩåIJį
    0.08
    çļĦ巨大
    0.08
    åºŀ大çļĦ
    0.08
    æķ°ä¸ĩ
    0.08
     billions
    0.08
    巨大
    0.08
    åľ
    0.08
    urang
    0.07
    Activations Density 0.060%

    No Known Activations