© 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. 58484
    Prev
    Next
    INDEX
    Explanations

    possibilities and facilities

    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
    æĦŁçļĦ
    -0.07
    éĺ²èĮĥæݪæĸ½
    -0.07
    orde
    -0.07
    ä¸įåIJĮç¨ĭ度
    -0.06
    áb
    -0.06
    viol
    -0.06
    è¿Ļåıªæĺ¯
    -0.06
    usti
    -0.06
    æĪĸçĶ¨
    -0.06
     ÑĤоп
    -0.06
    POSITIVE LOGITS
     whereas
    0.13
    èĢĮä¸Ķåľ¨
    0.11
     Whereas
    0.10
    èĢĮä¸Ķæľī
    0.10
    èĢĮä¸Ķ
    0.10
    ä¸Ķåľ¨
    0.10
    èĢĮä¸Ķæĺ¯
    0.09
    åĶ¯ä¸Ģä¸Ģ个
    0.09
    符åIJĪ
    0.09
    æĽ´ç¬¦åIJĪ
    0.09
    Activations Density 0.083%

    No Known Activations