© 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. 57282
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    aurus
    -0.07
    atis
    -0.06
    çĻ¾ç§ij
    -0.06
    stelling
    -0.06
    ewis
    -0.06
    Untitled
    -0.06
     unl
    -0.06
    ç½ijç«Ļ导èĪª
    -0.06
    èĶ½
    -0.06
    datas
    -0.06
    POSITIVE LOGITS
    æĽ´æĺ¯
    0.09
    çŃīçŃī
    0.08
    ,and
    0.08
    æ´»åĬ¨çŃī
    0.08
    æĽ´æĺ¯ä¸Ģ
    0.08
     enfin
    0.08
    äºļ
    0.08
    าะ
    0.08
    è¿ĻäºĽéĥ½
    0.08
    aky
    0.08
    Activations Density 0.541%

    No Known Activations