© 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. 32749
    Prev
    Next
    INDEX
    Explanations

    amplification

    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
    -0.11
    ÙĦد
    -0.09
    åįĬåĬŁ
    -0.09
    chter
    -0.08
    ÙħÙĨد
    -0.08
    eley
    -0.08
    ãģĵãĤį
    -0.07
    大åĬŁ
    -0.07
    æĪijæĿ¥è¯´
    -0.07
    abouts
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĢį
    0.09
    ÑĥÑīеÑģÑĤво
    0.08
    åĢįæķ°
    0.08
    мога
    0.08
    astia
    0.07
    æį¢ä»£
    0.07
    гол
    0.07
    vih
    0.07
    BaseContext
    0.07
    åĴĮæĶ¹è¿Ľ
    0.07
    Activations Density 0.017%

    No Known Activations