© 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. 22722
    Prev
    Next
    INDEX
    Explanations

    .h or .hpp file includes

    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
    ов
    -0.07
    ovic
    -0.06
    IPv
    -0.06
     lif
    -0.06
    utti
    -0.06
    ovu
    -0.06
    зов
    -0.06
    larg
    -0.06
    åı¦ä¸ĢåįĬ
    -0.06
     rach
    -0.06
    POSITIVE LOGITS
    æİ¡
    0.08
    мп
    0.08
    auta
    0.08
    letes
    0.07
    arde
    0.07
    ansom
    0.07
    odium
    0.06
    elib
    0.06
    arat
    0.06
    æĦıè§ģåıįé¦Ī
    0.06
    Activations Density 0.026%

    No Known Activations