© 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. 17687
    Prev
    Next
    INDEX
    Explanations

    module R

    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
    åģ·
    -0.07
    ulich
    -0.06
    æĿ¥ãģ®
    -0.06
    gh
    -0.06
    欢ä¹IJ
    -0.06
    Ø´ÙĦ
    -0.06
    æ¶ī
    -0.06
    _pag
    -0.06
    åıĭ好
    -0.06
     affair
    -0.06
    POSITIVE LOGITS
    ivil
    0.07
    ixel
    0.07
    arge
    0.07
    éĿ¢æĹł
    0.07
    éĻĪæĻĵ
    0.07
    pair
    0.07
    (pair
    0.07
    .rd
    0.07
    æľ¬ç«Ļ
    0.07
    consts
    0.07
    Activations Density 0.127%

    No Known Activations