© 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. 9704
    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
    urian
    -0.08
    äter
    -0.07
    ×ijר×Ļ
    -0.07
    anh
    -0.07
    лÑĮе
    -0.07
    urls
    -0.07
    ellas
    -0.07
    ivid
    -0.07
    èº
    -0.07
    ÐŁÐµÑĢе
    -0.06
    POSITIVE LOGITS
    wat
    0.07
    åłº
    0.07
    .blit
    0.07
    æݧåĪ¶ä¸Ńå¿ĥ
    0.07
    ä¸įæĺ¯åIJĹ
    0.06
    ism
    0.06
    .appendChild
    0.06
    çĶ·åĦ¿
    0.06
    -haired
    0.06
    dif
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.