© 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. 22318
    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
    ä½Ĩæĺ¯çİ°åľ¨
    -0.06
    ila
    -0.06
    裳
    -0.06
    ilas
    -0.06
    ÅĨ
    -0.06
    æľīä¿Ŀéļľ
    -0.06
    olec
    -0.06
    忽
    -0.06
    äºĮä¸ī
    -0.06
    æļĤæĹł
    -0.06
    POSITIVE LOGITS
    象
    0.08
    obb
    0.07
    unge
    0.07
    hos
    0.07
    ä¹ĭæģ©
    0.07
    èĩªå·±èº«ä¸Ĭ
    0.07
    è·¯éĢı
    0.07
     Embassy
    0.07
    צע
    0.07
    Ñģполни
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.