© 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. 28311
    Prev
    Next
    INDEX
    Explanations

    mathematical limits and roots

    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
    emos
    -0.07
    mino
    -0.07
    adona
    -0.06
    elle
    -0.06
    &a
    -0.06
    Wunused
    -0.06
    สล
    -0.06
    ä¸į认è¯Ĩ
    -0.06
    ě[
    -0.06
    AINED
    -0.06
    POSITIVE LOGITS
    ĭ
    0.09
    égi
    0.08
    ispers
    0.07
    ิà¹Īม
    0.07
    poser
    0.07
    loor
    0.07
    quirer
    0.07
    водÑı
    0.07
    rij
    0.07
    ¢
    0.07
    Activations Density 0.002%

    No Known Activations