© 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. 19119
    Prev
    Next
    INDEX
    Explanations

    contextual outcomes or descriptors

    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
    åĽŀäºĭ
    -0.08
    ä»Ģä¹Īåı«
    -0.07
    /misc
    -0.07
    aggable
    -0.07
     ...)
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    æĸĩç«łäºĨ
    -0.07
    ä¸ĭæľī
    -0.07
    bidden
    -0.07
    /o
    -0.07
    POSITIVE LOGITS
     inoltre
    0.18
     however
    0.15
    however
    0.14
    ä¹ŁåĽłæѤ
    0.13
     furthermore
    0.13
     же
    0.13
     therefore
    0.13
     обаÑĩе
    0.12
     azonban
    0.12
     tehát
    0.12
    Activations Density 2.441%

    No Known Activations