© 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. 23818
    Prev
    Next
    INDEX
    Explanations

    0s and Cs

    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
    aci
    -0.07
     [.
    -0.06
    ARIO
    -0.06
    ÙĬتÙĬÙĨ
    -0.06
    æİĮæı¡
    -0.06
     y
    -0.06
    bes
    -0.06
    [email
    -0.06
    razio
    -0.06
    -0.06
    POSITIVE LOGITS
    çݲçıij
    0.08
    íĮ
    0.08
    模çīĪ
    0.07
    æIJľç´¢ç»ĵæŀľ
    0.07
    artos
    0.07
     sär
    0.07
    ëĤĺ무
    0.07
    ustr
    0.07
    tic
    0.07
     Wich
    0.07
    Activations Density 0.013%

    No Known Activations