© 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. 50438
    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
    úi
    -0.08
    -turned
    -0.07
    ilyn
    -0.07
    å²IJ
    -0.07
    optgroup
    -0.07
    zer
    -0.07
    maÃŁen
    -0.07
    aringan
    -0.06
    麻麻
    -0.06
    ungsver
    -0.06
    POSITIVE LOGITS
    çħ§çĽ¸
    0.07
    æ§Ľ
    0.07
    æĻĸ
    0.06
    .gov
    0.06
    ahn
    0.06
    _sg
    0.06
    anca
    0.06
    åĩłä¸ĭ
    0.06
    ä¸İåIJĮåѦ
    0.06
    ë§IJ
    0.06
    Activations Density 0.000%

    No Known Activations