© 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. 48887
    Prev
    Next
    INDEX
    Explanations

    example text/code structures

    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
    idy
    -0.07
    uc
    -0.07
    olic
    -0.07
    oling
    -0.07
    ills
    -0.06
     indirect
    -0.06
    åĬłä¸Ĭ
    -0.06
    indle
    -0.06
    ÙĪÙĪ
    -0.06
    天æĢ§
    -0.06
    POSITIVE LOGITS
    åıĪå¦Ĥ
    0.10
    åIJĮæł·æĺ¯
    0.10
    ä¹ŁåIJĮæł·
    0.09
     magari
    0.08
    åľ¨åIJĮä¸Ģ
    0.08
    åIJĮãģĺ
    0.08
    åIJĮä¸Ģ个
    0.08
    fels
    0.08
    çħ§æł·
    0.08
    åIJĮæł·çļĦ
    0.08
    Activations Density 0.098%

    No Known Activations