© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30071
    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
    course
    -0.08
    æĸ°åŃ¦æľŁ
    -0.07
    kea
    -0.06
    åĴĮæĸ¹æ³ķ
    -0.06
    èºģ
    -0.06
     $(
    -0.06
    äºĭæĢģ
    -0.06
    ledge
    -0.06
    tox
    -0.06
    _issues
    -0.06
    POSITIVE LOGITS
    emics
    0.08
    çĴIJ
    0.07
    åĨĻæĻ¯
    0.07
    emia
    0.07
    emic
    0.07
    鼰
    0.07
     ATTRIBUTE
    0.07
    ä¸įäºĨçļĦ
    0.06
     advertise
    0.06
    åıijå¸ĸ
    0.06
    Activations Density 0.000%

    No Known Activations