© 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. 31163
    Prev
    Next
    INDEX
    Explanations

    intestinal diseases

    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
    omp
    -0.09
    çļĦèĥĮåIJİ
    -0.07
    ç«ĭäºİ
    -0.06
    ç«ĭåľ¨
    -0.06
    isir
    -0.06
    quo
    -0.06
    çĶŁäºİ
    -0.06
    ç»ıèIJ¥é¡¹çĽ®
    -0.06
     ÙħÙĤت
    -0.06
    ĸ
    -0.06
    POSITIVE LOGITS
    éķ¿åº¦
    0.08
    èłķåĬ¨
    0.08
    çŃīå¤Ħ
    0.08
    íĢ´
    0.08
     length
    0.08
     Length
    0.08
    _length
    0.08
    length
    0.07
    .Receive
    0.07
    -wide
    0.07
    Activations Density 0.032%

    No Known Activations