© 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. 2448
    Prev
    Next
    INDEX
    Explanations

    religious titles, technical terms, programming concepts

    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
    ÏĥÏĩ
    -0.08
    ãĥĭãĥĥãĤ¯
    -0.08
    prech
    -0.07
    ä¹ĭä¸į
    -0.07
    Ñĥда
    -0.07
    .persist
    -0.07
    erven
    -0.07
    prof
    -0.07
     possibil
    -0.07
     Wib
    -0.07
    POSITIVE LOGITS
    ade
    0.08
    iner
    0.08
    æĹłåħ³
    0.07
    quat
    0.07
    its
    0.07
    æ°ı
    0.07
     sondern
    0.07
    èĢĮæĺ¯
    0.07
    although
    0.07
    unc
    0.07
    Activations Density 0.012%

    No Known Activations