© 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. 50481
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with sqrt

    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
    agrid
    -0.08
    umpf
    -0.07
    æĭ¨æīĵçĶµè¯Ŀ
    -0.07
    'field
    -0.07
    æīĵå¼Ģæīĭæľº
    -0.07
     unbe
    -0.07
    )o
    -0.07
    issor
    -0.07
    unct
    -0.07
    äk
    -0.07
    POSITIVE LOGITS
    ıb
    0.08
    à¸ķรี
    0.07
    å°ıæľ¨
    0.07
    ambe
    0.06
    cas
    0.06
    宿
    0.06
    _answer
    0.06
    第äºĮ大
    0.06
    åį¡çī¹
    0.06
    DOC
    0.06
    Activations Density 0.018%

    No Known Activations