© 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. 7500
    Prev
    Next
    INDEX
    Explanations

    medical terms, brands, technologies

    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
    缴æİ¥æĪĸ
    -0.08
    åIJĪåIJĮæŶ
    -0.08
    以åıĬå¦Ĥä½ķ
    -0.07
    Ù°
    -0.07
    çļĦéĤ£æł·
    -0.07
    abouts
    -0.07
    attended
    -0.07
     Industr
    -0.07
    ãģŁãģ¡
    -0.07
    èĢĮä¸Ķæĺ¯
    -0.07
    POSITIVE LOGITS
     же
    0.13
    åĺĽ
    0.12
     infatti
    0.12
     natomiast
    0.11
     enim
    0.10
    èµ·è§ģ
    0.10
     voici
    0.09
     bowiem
    0.09
    ä¹ĭæīĢ以
    0.09
     voilÃł
    0.09
    Activations Density 0.723%

    No Known Activations