© 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. 8061
    Prev
    Next
    INDEX
    Explanations

    I ask the question

    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
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    -0.06
    èĪ
    -0.06
    _mock
    -0.06
    lig
    -0.06
    åĭ¤
    -0.06
    å²ij
    -0.06
     awful
    -0.05
    bach
    -0.05
    Âł
    -0.05
    istente
    -0.05
    POSITIVE LOGITS
    Ñħоз
    0.09
    ëį©
    0.08
    ftime
    0.08
    бин
    0.08
    благо
    0.08
    Ease
    0.08
    WORDS
    0.07
    interop
    0.07
     Dua
    0.07
    éĿ¢æĹł
    0.07
    Activations Density 0.035%

    No Known Activations