© 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. 46365
    Prev
    Next
    INDEX
    Explanations

    level of experience or expertise

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    askan
    -0.08
    æŁĶ软çļĦ
    -0.08
    æŁĶå¼±
    -0.08
    _soft
    -0.08
    温æļĸåĴĮ
    -0.07
    Descriptor
    -0.07
    emez
    -0.07
     softer
    -0.07
    aname
    -0.07
    软çļĦ
    -0.07
    POSITIVE LOGITS
     sophisticated
    0.12
     sofistic
    0.09
     sophistication
    0.09
    级åĪ«çļĦ
    0.08
    çŃīä¸ĵä¸ļ
    0.08
    ä»ĸ们已ç»ı
    0.08
    -level
    0.08
     familiar
    0.08
     advanced
    0.08
    æ°´å¹³çļĦ
    0.08
    Activations Density 0.076%

    No Known Activations