© 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. 38460
    Prev
    Next
    INDEX
    Explanations

    Hungary

    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
     ìĨį
    -0.07
    ingt
    -0.07
    æĮºèº«
    -0.07
    era
    -0.07
    书åIJ§
    -0.07
    زاÙĦ
    -0.07
    饶
    -0.07
    imore
    -0.07
    ée
    -0.06
    occ
    -0.06
    POSITIVE LOGITS
    צ×ķ×¢
    0.07
    åıĪåĥı
    0.07
    æĹ¢ä¸į
    0.07
    vani
    0.07
    ä¸ĭæľī
    0.07
    ä¸įåIJĮæĦı
    0.07
    峪
    0.06
    asonic
    0.06
     Camb
    0.06
    (".",
    0.06
    Activations Density 0.043%

    No Known Activations