© 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. 32928
    Prev
    Next
    INDEX
    Explanations

    patent literature, technical field

    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
    çĶ»ä¸Ĭ
    -0.07
     lohnt
    -0.07
    ī´
    -0.07
    ÛĮÙĩ
    -0.07
    athi
    -0.07
    GetComponent
    -0.07
    cola
    -0.07
    elaar
    -0.07
    zinho
    -0.07
    bilt
    -0.07
    POSITIVE LOGITS
    æīĵåıij
    0.07
    mr
    0.07
    没ä»Ģä¹Ī
    0.07
     MANAG
    0.07
    à¥ī
    0.06
    åı¯èĥ½æľī
    0.06
    rag
    0.06
    åħ·
    0.06
    inia
    0.06
     ASAP
    0.06
    Activations Density 0.003%

    No Known Activations