© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20787
    Prev
    Next
    INDEX
    Explanations

    medical procedure 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
     bur
    -0.06
    广ä¹ī
    -0.06
     former
    -0.06
     L
    -0.06
    ovo
    -0.06
    éŨå°Ĩ
    -0.06
    ä¸įè§ģ
    -0.06
    apest
    -0.05
    appen
    -0.05
    ä¸Ĭè¿Ľ
    -0.05
    POSITIVE LOGITS
    iefer
    0.08
    bjerg
    0.08
    .shtml
    0.08
    å§ĭ
    0.08
    çIJ¥
    0.08
    æĸĽ
    0.08
    çĥŃéŨæĸĩç«ł
    0.08
    /***/
    0.08
    æ¡Ī件éĢĤçĶ¨æ³ķå¾ĭ
    0.08
    å¿ħä¸įåı¯
    0.08
    Activations Density 0.220%

    No Known Activations