© 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. 48768
    Prev
    Next
    INDEX
    Explanations

    mathematical notations with symbols

    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
    aid
    -0.07
    ledes
    -0.06
    acto
    -0.06
    akk
    -0.06
    ายà¸Ļ
    -0.06
    juk
    -0.06
    :no
    -0.06
    pest
    -0.06
    -/
    -0.06
    æ²³æµģåŁŁ
    -0.06
    POSITIVE LOGITS
    ervals
    0.09
    iraz
    0.08
    icola
    0.08
    ×ĺ×Ļ×Ŀ
    0.07
    æĺµ
    0.07
    leÅŁ
    0.07
    ancock
    0.07
    Öģ
    0.07
    ISTR
    0.07
    impse
    0.07
    Activations Density 0.005%

    No Known Activations