© 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. 57320
    Prev
    Next
    INDEX
    Explanations

    court citations

    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
    ses
    -0.07
    æĥħ
    -0.07
     harta
    -0.06
    éĺĻ
    -0.06
     ster
    -0.06
     e
    -0.06
    ê³ĦìĹIJ
    -0.06
    缸
    -0.06
    åīįè¡ĮçļĦ
    -0.06
    plan
    -0.06
    POSITIVE LOGITS
    FromArray
    0.08
    illus
    0.08
    à¸Ĭีà¸ŀ
    0.08
    enius
    0.08
    heck
    0.08
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    astes
    0.07
    æľ¬å¸ĸ
    0.07
    arão
    0.07
    imeo
    0.07
    Activations Density 0.011%

    No Known Activations