© 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. 32219
    Prev
    Next
    INDEX
    Explanations

    cluster or clusters

    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
    ắt
    -0.08
    à¸ĩาม
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    สà¹Į
    -0.07
    åĬ©äºİ
    -0.07
     xuôi
    -0.07
    /left
    -0.07
    alan
    -0.07
    neh
    -0.07
     transmis
    -0.07
    POSITIVE LOGITS
    ваннÑı
    0.08
    ë©į
    0.08
    dorf
    0.08
    窿
    0.08
    ë§ģ
    0.08
    mates
    0.08
    ings
    0.08
    ยà¹Īà¸Ńย
    0.08
    رات
    0.08
    arkin
    0.08
    Activations Density 0.012%

    No Known Activations