© 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. 4054
    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
    çĭŃ
    -0.07
    éĤ£äºĽ
    -0.07
    iaan
    -0.06
    à¤ľà¤°
    -0.06
    ÑİÑĢи
    -0.06
    é¼
    -0.06
    odr
    -0.06
     Abrams
    -0.06
     Barnes
    -0.06
    yk
    -0.06
    POSITIVE LOGITS
    .appspot
    0.08
    ä¹ŀ
    0.07
    æĪŁ
    0.07
    غر
    0.07
    å®£ä¼łèµĦæĸĻ
    0.06
    _fixed
    0.06
    å¿ĺä¸įäºĨ
    0.06
    tram
    0.06
    _cli
    0.06
    oine
    0.06
    Activations Density 0.000%

    No Known Activations