© 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. 30229
    Prev
    Next
    INDEX
    Explanations

    css variable assignments

    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
    ÑĦÑĢа
    -0.06
    æµ®çĶŁ
    -0.06
     Reh
    -0.06
    oke
    -0.06
    åѦå¾Ĺ
    -0.06
    DS
    -0.06
     mim
    -0.06
    pressa
    -0.06
    мÑĥÑĤ
    -0.05
     Casas
    -0.05
    POSITIVE LOGITS
    èIJĦ
    0.08
     likewise
    0.08
    chal
    0.07
     altrettanto
    0.07
    cheng
    0.07
    -trash
    0.07
    åIJĮä¸Ĭ
    0.07
    urname
    0.07
    lien
    0.07
    alp
    0.07
    Activations Density 0.078%

    No Known Activations