© 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. 33438
    Prev
    Next
    INDEX
    Explanations

    likely words following ÂŃ

    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
    á½
    -0.06
    ury
    -0.06
    ÑĥÑĤÑĮ
    -0.06
     Beard
    -0.06
    ั
    -0.06
     reflection
    -0.06
    æĶ¿
    -0.06
    ç«ŀäºīæĢ§
    -0.06
     Reflection
    -0.06
     reflections
    -0.06
    POSITIVE LOGITS
    ắn
    0.09
    anean
    0.08
    ×Ļר×Ļ×Ŀ
    0.08
    ugna
    0.07
    lyph
    0.07
    ikus
    0.07
    大ä¸įäºĨ
    0.07
    LoginPage
    0.07
    icode
    0.07
    à¸Ħà¸Ķี
    0.07
    Activations Density 0.002%

    No Known Activations