© 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. 10401
    Prev
    Next
    INDEX
    Explanations

    exercises and activities

    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
    æĸ°ä¹¦æݨèįIJ
    -0.07
     optim
    -0.06
     optimal
    -0.06
    æı½
    -0.06
    Hint
    -0.06
    çIJĨæĥ³çļĦ
    -0.06
     refin
    -0.06
     ê°ķì¢Į
    -0.06
    ä¼ĺåĮĸçļĦ
    -0.06
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.06
    POSITIVE LOGITS
    çĴ¨
    0.08
    eran
    0.08
    isser
    0.07
     checkboxes
    0.07
    å¿ħçŃĶ
    0.07
    課é¡Į
    0.07
     подле
    0.07
    __:
    0.07
    bst
    0.07
    robe
    0.07
    Activations Density 0.008%

    No Known Activations