© 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. 1133
    Prev
    Next
    INDEX
    Explanations

    medical conditions and events

    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
    ç¿İ
    -0.08
    ÑĢÑĥм
    -0.08
    æ¯Ĵ
    -0.07
    ادÙħ
    -0.07
     {[
    -0.07
    allery
    -0.07
    inium
    -0.07
     hastily
    -0.07
    _tolerance
    -0.07
    nds
    -0.07
    POSITIVE LOGITS
    æŁIJäºĽ
    0.12
    èĻ½çĦ¶æ²¡æľī
    0.12
    èĻ½çĦ¶ä¸įæĺ¯
    0.11
    åľ¨æŁIJäºĽ
    0.11
     certain
    0.11
     Certain
    0.11
    ä¹Łæľīä¸Ģå®ļçļĦ
    0.10
    å°¤åħ¶æĺ¯
    0.09
    æľīä¸Ģå®ļ
    0.09
    æĪĸå¤ļæĪĸå°ij
    0.09
    Activations Density 0.305%

    No Known Activations