© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8345
    Prev
    Next
    INDEX
    Explanations

    black breath

    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
    anson
    -0.06
    Beh
    -0.06
    оÑĢе
    -0.06
    æĭŁ
    -0.06
    adesh
    -0.06
    оÑĤов
    -0.06
    ore
    -0.06
     Beh
    -0.06
    _splits
    -0.06
    дел
    -0.06
    POSITIVE LOGITS
    缸åħ³æݨèįIJ
    0.08
    edList
    0.07
     predic
    0.07
    fixtures
    0.07
    igits
    0.07
    ä¸ĢåĨį
    0.07
    ä»Ĭ天å°ıç¼ĸ
    0.07
    è³Ģ
    0.07
    ilyn
    0.07
    vais
    0.07
    Activations Density 0.004%

    No Known Activations