© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15939
    Prev
    Next
    INDEX
    Explanations

    unique characters and numbers

    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
    zion
    -0.06
    hä
    -0.06
    öh
    -0.06
     hong
    -0.06
    æĹłæ³ķæŃ£å¸¸
    -0.06
    c
    -0.06
    tai
    -0.06
    zioni
    -0.05
    ↵
    -0.05
    æĸ°åĬłåĿ¡
    -0.05
    POSITIVE LOGITS
    åľĥ
    0.08
    epat
    0.08
    eram
    0.08
    æĸĵ
    0.08
    ãģ«ãģªãĤĮãĤĭ
    0.08
    edor
    0.08
    ertools
    0.08
    精深
    0.07
    unjung
    0.07
    lobal
    0.07
    Activations Density 0.048%

    No Known Activations