© 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. 40695
    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
     Tad
    -0.08
    ê°Ī
    -0.08
    acruz
    -0.07
    дав
    -0.07
    ä¸įä¸ĭæĿ¥
    -0.07
    ä¸įæį¢
    -0.07
    æľ¬æĬ¥
    -0.07
    ä¸įäºĨ
    -0.07
     cat
    -0.07
    /Table
    -0.07
    POSITIVE LOGITS
    ÄĽn
    0.07
    漫
    0.07
    èĩªå·±
    0.07
    ugel
    0.07
    壬
    0.07
    -rounded
    0.07
    è°IJ
    0.06
    仲
    0.06
    cca
    0.06
    æ±ĩ
    0.06
    Activations Density 0.000%

    No Known Activations