© 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. 26160
    Prev
    Next
    INDEX
    Explanations

    medical procedure words

    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
    éĹ®é¢ĺæŶ
    -0.09
    endam
    -0.08
    åIJĪåIJĮæŶ
    -0.08
    ,to
    -0.07
    /from
    -0.07
    æŶéĹ´æĿ¥
    -0.07
    à¸ĵะ
    -0.07
    itzer
    -0.07
    öh
    -0.06
    ,on
    -0.06
    POSITIVE LOGITS
    两åѦä¸Ģåģļ
    0.09
    èµ·è§ģ
    0.09
    ÙĮ
    0.08
     коÑĤоÑĢого
    0.08
    à¸Īึà¸ĩ
    0.08
    lah
    0.08
     навеÑĢное
    0.08
     namely
    0.08
     voici
    0.07
     voilÃł
    0.07
    Activations Density 0.505%

    No Known Activations