© 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. 61944
    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
    ä¸ī大
    -0.07
     mets
    -0.07
    对åħ¶ä»ĸ
    -0.07
    igin
    -0.07
    irable
    -0.06
    ä¸ī个æĸ¹éĿ¢
    -0.06
    iran
    -0.06
    å·´
    -0.06
    ä»Ģä¹Īéĥ½ä¸į
    -0.06
    RV
    -0.06
    POSITIVE LOGITS
    daq
    0.07
    ä½łç»ĻæĪij
    0.07
    iets
    0.07
    eux
    0.06
    coal
    0.06
    并称
    0.06
    ÅĦ
    0.06
     involves
    0.06
    립
    0.06
    æĺ¯ä¸ĢæĿ¡
    0.06
    Activations Density 0.000%

    No Known Activations