© 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. 20252
    Prev
    Next
    INDEX
    Explanations

    reflects something or the

    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
    æŀĦ建åĴĮè°IJ
    -0.08
    iot
    -0.07
    lah
    -0.07
    åĻľ
    -0.07
     Hwy
    -0.07
    fredo
    -0.07
    xious
    -0.07
    声åIJį
    -0.07
    el
    -0.07
    缸åħ³æĸĩç«ł
    -0.07
    POSITIVE LOGITS
    à¸ĸึà¸ĩà¸ģาร
    0.10
    åıįæĺł
    0.09
    .DeepEqual
    0.08
     ë°ĺìĺģ
    0.08
    åıįæĺłäºĨ
    0.08
    ä¸Ģæĸij
    0.08
    à¸ĸึà¸ĩà¸Ħวาม
    0.08
     changing
    0.08
    ager
    0.08
    roring
    0.08
    Activations Density 0.015%

    No Known Activations