© 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. 12018
    Prev
    Next
    INDEX
    Explanations

    innate immune, enteral nutrition

    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
    ITO
    -0.07
    æģŃ
    -0.06
    æĮºèº«
    -0.06
    atau
    -0.06
    åįĬæŃ¥
    -0.06
    æķ¬
    -0.06
    icap
    -0.06
     MOT
    -0.06
    åIJİæĦŁ
    -0.06
    itelj
    -0.06
    POSITIVE LOGITS
    ä¸Ķåħ·æľī
    0.09
    ä¸Ķæľī
    0.08
    èĢĮä¸Ķæĺ¯
    0.08
    ä¸Ķåľ¨
    0.07
    .nasa
    0.07
    åIJĦé¢ĨåŁŁ
    0.07
    _descriptor
    0.07
     Ejem
    0.07
    ä¸Ķ
    0.07
    _DER
    0.07
    Activations Density 0.419%

    No Known Activations