© 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. 38007
    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
    <strong
    -0.08
    åľºæĻ¯
    -0.08
    дже
    -0.07
    ä¸īæĹł
    -0.07
    羣æĬĵ
    -0.07
     scenari
    -0.07
    iak
    -0.07
     erhoben
    -0.07
    åħ¨åľº
    -0.07
    æĹłéĺ»
    -0.07
    POSITIVE LOGITS
     imbalance
    0.08
    ãĥIJãĥ©ãĥ³ãĤ¹
    0.08
    åģı离
    0.08
    失衡
    0.08
    ä¸į平衡
    0.07
     asym
    0.07
     trend
    0.07
     ratios
    0.07
    åŃķèĤ²
    0.07
    çļĦè¶ĭåĬ¿
    0.07
    Activations Density 0.000%

    No Known Activations