© 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. 27524
    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
    pective
    -0.07
    èĮĦ
    -0.07
    setattr
    -0.07
    ported
    -0.07
    illage
    -0.06
    beit
    -0.06
    orat
    -0.06
     ترÛĮÙĨ
    -0.06
    -0.06
    åĩºèĩª
    -0.06
    POSITIVE LOGITS
    unto
    0.08
    æľĭ
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    Injector
    0.07
    ä»Ĭ
    0.07
    ä¹ĭéŨ
    0.07
    æįĮ
    0.07
    êµ°
    0.07
    ä¼ģä¸ļä¸ļåĬ¡
    0.07
     synerg
    0.07
    Activations Density 0.000%

    No Known Activations