© 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. 42995
    Prev
    Next
    INDEX
    Explanations

    inception to dates

    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
    çĿĢçĶ¨
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    antine
    -0.07
    ron
    -0.07
    人类çļĦ
    -0.07
     prop
    -0.07
    #error
    -0.07
    veled
    -0.07
    idy
    -0.07
    .complete
    -0.07
    POSITIVE LOGITS
    riot
    0.07
    saf
    0.06
     convention
    0.06
    ervis
    0.06
     reunion
    0.06
    emory
    0.06
    æĽ
    0.06
    çĬ¯äºº
    0.06
    æĭ¬
    0.06
    tart
    0.06
    Activations Density 0.003%

    No Known Activations