© 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. 24315
    Prev
    Next
    INDEX
    Explanations

    biological and medical 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
    ç¥ŀéĩĩ
    -0.07
    åĬ
    -0.07
    gänge
    -0.07
     thơ
    -0.07
    efeld
    -0.07
    稿
    -0.07
    ฯ
    -0.07
    .moveTo
    -0.07
    æĸĩ稿
    -0.06
    ä¸ĭè¿°
    -0.06
    POSITIVE LOGITS
    oura
    0.08
    cium
    0.07
    sd
    0.07
     Firstly
    0.07
    ovnÃŃ
    0.07
    ä¸ĢæĮĩ
    0.06
    itre
    0.06
    emment
    0.06
    imon
    0.06
    pg
    0.06
    Activations Density 3.027%

    No Known Activations