© 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. 28810
    Prev
    Next
    INDEX
    Explanations

    medical procedures and states

    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
     Kirim
    -0.08
    íģIJ
    -0.07
    èĪªç«Ļ
    -0.07
    çĽijåĪ¶
    -0.07
    ilog
    -0.07
    ļĮ
    -0.07
    ê·ľ
    -0.07
     Retrou
    -0.07
    inste
    -0.07
     inv
    -0.07
    POSITIVE LOGITS
    æ¸ħ空
    0.09
     temporarily
    0.09
    å½»åºķ
    0.09
    สà¸Ļิà¸Ĺ
    0.09
    æŃ£åľ¨è¿Ľè¡Į
    0.09
     Disconnect
    0.08
    å½»åºķçļĦ
    0.08
    åĪĩæĸŃ
    0.08
    æļĤæŶ
    0.08
    çļĦå®īåħ¨
    0.08
    Activations Density 0.120%

    No Known Activations