© 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. 7622
    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
    ker
    -0.07
    eland
    -0.07
    crest
    -0.07
    ¾
    -0.06
    åĽ°å¢ĥ
    -0.06
     Smy
    -0.06
    ild
    -0.06
    ä¸įåIJĪçIJĨ
    -0.06
    è§ĴçļĦ
    -0.06
    ara
    -0.06
    POSITIVE LOGITS
    åı¦å¤ĸè¿ĺæľī
    0.07
    åįİéĺ³
    0.07
    çļĦè¿ĺæľī
    0.07
    tart
    0.07
    åŁŁç½ij
    0.07
    chnik
    0.07
    å®Ŀé¾Ļ
    0.07
     spéc
    0.07
    åįİå±±
    0.07
    /detail
    0.07
    Activations Density 0.000%

    No Known Activations