© 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. 28435
    Prev
    Next
    INDEX
    Explanations

    abscesses and infections

    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
    æĿIJ
    -0.08
     Boeh
    -0.07
    è°ĥæݧ
    -0.07
     Liver
    -0.07
     gifted
    -0.07
    æĬĹçĻĮ
    -0.07
    érist
    -0.07
    羿
    -0.07
    ScreenWidth
    -0.06
    è°ĥèĬĤ
    -0.06
    POSITIVE LOGITS
     bacterial
    0.13
     infection
    0.12
    ç»ĨèıĮæĦŁæŁĵ
    0.12
     bacter
    0.12
     infections
    0.12
    æĦŁæŁĵçļĦ
    0.11
    æĦŁæŁĵ
    0.11
    ç»ĨèıĮ
    0.11
     bakteri
    0.11
     bacteria
    0.10
    Activations Density 0.230%

    No Known Activations