© 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. 39325
    Prev
    Next
    INDEX
    Explanations

    math notation or inline equations

    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
    åı¯æĢľ
    -0.08
    åĽłä¸ºåıªæľī
    -0.08
    åĽłä¸ºåľ¨
    -0.07
    iser
    -0.07
     campa
    -0.07
    umbo
    -0.07
    UED
    -0.07
    enko
    -0.06
    ä¼łç»ŁçļĦ
    -0.06
    ipo
    -0.06
    POSITIVE LOGITS
    è°Ĵ
    0.08
    æłĩåħµ
    0.08
    ாள
    0.07
    eczy
    0.07
    æĽ³
    0.07
    ä¹ħ
    0.07
    orde
    0.07
    åĩł
    0.06
    гоÑĢа
    0.06
    juang
    0.06
    Activations Density 0.073%

    No Known Activations