© 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. 28631
    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
    uits
    -0.09
    uscita
    -0.07
    otta
    -0.07
    ularity
    -0.07
    马æĸ¯
    -0.07
    à¦Ĺà§ģল
    -0.07
    halte
    -0.07
    为å®ĺ
    -0.06
    为å¸Ī
    -0.06
    quire
    -0.06
    POSITIVE LOGITS
    åĬ©æīĭ
    0.09
    Wide
    0.07
    åĬ©
    0.07
    ted
    0.07
    ÙĨج
    0.07
    æĸ°ä¸Ģ
    0.07
    çij¾
    0.07
    ernet
    0.07
    GP
    0.06
    anical
    0.06
    Activations Density 0.000%

    No Known Activations