© 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. 30536
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and inequalities

    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
    aldi
    -0.08
    dah
    -0.08
     contrário
    -0.08
    anken
    -0.08
     IReadOnly
    -0.07
    è«Ń
    -0.07
    ñado
    -0.07
    mene
    -0.07
    anzo
    -0.07
    dbuf
    -0.07
    POSITIVE LOGITS
    ç¿
    0.07
    wski
    0.07
    isson
    0.06
    lagt
    0.06
    ếm
    0.06
    丰èĥ¸
    0.06
    ero
    0.06
    пло
    0.06
    zeÅĽ
    0.06
    ä¹ĭæĥħ
    0.06
    Activations Density 0.016%

    No Known Activations