© 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. 32520
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Teixe
    -0.08
    娥
    -0.07
    pson
    -0.07
    éªı
    -0.07
    ajú
    -0.07
    æľīäºĨ
    -0.07
    RequestMethod
    -0.07
    æĭľ
    -0.07
     pros
    -0.06
    "d
    -0.06
    POSITIVE LOGITS
    ame
    0.07
    å·²æĪIJåĬŁ
    0.07
    Smith
    0.07
    åIJĪä½ľäº¤æµģ
    0.06
    tempt
    0.06
    /Product
    0.06
    SMART
    0.06
    à¸Ĭà¸Ļ
    0.06
    fix
    0.06
     euler
    0.06
    Activations Density 0.749%

    No Known Activations

    This feature has no known activations.