© 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. 43710
    Prev
    Next
    INDEX
    Explanations

    mathematical setup therefore

    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
    æ¢ĵ
    -0.09
    erta
    -0.07
    erschutz
    -0.07
    ä¸įéĹ®
    -0.07
    avs
    -0.07
    为ä¿Ŀè¯ģ
    -0.07
    çĨĶ
    -0.07
    avat
    -0.07
    ä¸Ģå¥Ĺ
    -0.07
     mist
    -0.07
    POSITIVE LOGITS
    便äºİ
    0.08
     Bever
    0.08
     decomposition
    0.07
    SetUp
    0.07
    容æĺĵå¼ķèµ·
    0.07
    éĩĮéĿ¢çļĦ
    0.07
    第åħ«å±Ĭ
    0.07
    ibble
    0.07
    rim
    0.07
    etan
    0.07
    Activations Density 0.006%

    No Known Activations