© 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. 12154
    Prev
    Next
    INDEX
    Explanations

    apartment size

    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
    ter
    -0.07
    æŃ£ä¸Ń
    -0.07
     Ñĥв
    -0.06
    ãģ«ãģĦãĤĭ
    -0.06
    __/
    -0.06
     Workplace
    -0.06
    InstanceOf
    -0.06
    å¯¹çĽ¸åħ³
    -0.06
    ãģ«ãģĤãĤĭ
    -0.06
    轨
    -0.06
    POSITIVE LOGITS
    ussi
    0.10
    åIJįä¸ĭ
    0.08
    erar
    0.08
    uset
    0.08
    allest
    0.07
    ogens
    0.07
    à¹Ģà¸ģียรà¸ķิ
    0.07
    stor
    0.07
     relocated
    0.07
    ä»ĸç«ŁçĦ¶
    0.07
    Activations Density 0.138%

    No Known Activations