© 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. 60781
    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
    æĬ¼
    -0.07
    ç»ĵæŀĦ设计
    -0.07
    åIJĮå¿Ĺ们
    -0.07
     Tier
    -0.07
    enance
    -0.06
     physically
    -0.06
    ekon
    -0.06
     controller
    -0.06
    æݺ
    -0.06
    asti
    -0.06
    POSITIVE LOGITS
    äºĭäºĭ
    0.08
    ç¹ĭ
    0.07
    unner
    0.07
    Inlining
    0.07
    à¤ķà¥įषण
    0.07
     erzeugt
    0.07
     воÑĢо
    0.07
    qrt
    0.07
    chnik
    0.07
    çŁ¥ç½ij
    0.07
    Activations Density 0.000%

    No Known Activations