© 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. 47466
    Prev
    Next
    INDEX
    Explanations

    mathematics 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
    æ»´
    -0.08
    å¹Į
    -0.07
    ä»İä¸Ģ个
    -0.07
    æľĿå¤ķ
    -0.07
     Dro
    -0.07
    chan
    -0.07
    éĩıå°ij
    -0.07
    waar
    -0.06
    stan
    -0.06
    abat
    -0.06
    POSITIVE LOGITS
    æľĢæĸ°æĽ´æĸ°
    0.08
    ake
    0.08
    еÑģÑģи
    0.07
    íıŃ
    0.07
    egen
    0.07
    achen
    0.07
    리ìĸ´
    0.07
    omes
    0.07
    ’B
    0.07
    rvine
    0.07
    Activations Density 0.001%

    No Known Activations