© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62694
    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
    miss
    -0.07
    laub
    -0.07
    icing
    -0.07
     Rede
    -0.07
    omon
    -0.07
    天
    -0.06
    Guy
    -0.06
    izon
    -0.06
    åľ¨ç»Ļ
    -0.06
    omen
    -0.06
    POSITIVE LOGITS
    ovia
    0.07
    åīįåIJİçļĦ
    0.07
    åłº
    0.07
    pecific
    0.07
    ecn
    0.07
     random
    0.07
    è¿IJä¼ļ
    0.07
    交åĬŀ
    0.07
     specific
    0.06
     prior
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.