© 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. 11953
    Prev
    Next
    INDEX
    Explanations

    polynomial factorization

    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
    atural
    -0.08
    &r
    -0.07
    ież
    -0.07
    hares
    -0.07
    _increment
    -0.07
    urie
    -0.07
    å°ĶèĴĻ
    -0.07
    à¸Ķà¹Īวà¸Ļ
    -0.07
    åħħ
    -0.07
    endl
    -0.07
    POSITIVE LOGITS
    ÄĻk
    0.07
    istet
    0.07
    andalone
    0.07
    .sock
    0.07
    åħ³äºİè¿Ľä¸ĢæŃ¥
    0.06
    éļĻ
    0.06
    ubic
    0.06
    cket
    0.06
    åĩºä¹İ
    0.06
    ëŀĺ
    0.06
    Activations Density 0.009%

    No Known Activations