© 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. 33924
    Prev
    Next
    INDEX
    Explanations

    children attending or delivered

    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
    aging
    -0.08
    à¸Ħà¹Į
    -0.08
    ally
    -0.08
    anky
    -0.08
    hift
    -0.07
    ÚĺÙĩ
    -0.07
    æīĭæľºç«Ļ
    -0.07
    ÙģÛĮ
    -0.07
    åħ¨ä¹¦
    -0.07
    коÑģÑĤи
    -0.07
    POSITIVE LOGITS
    hood
    0.13
    ÑĪек
    0.11
    åĴĮ家éķ¿
    0.10
    åıĬ家éķ¿
    0.09
    åĢijçļĦ
    0.09
    ateau
    0.09
    ÅĦstwo
    0.08
    uate
    0.08
    jenigen
    0.08
    ä¸Ģè¾Ī
    0.08
    Activations Density 0.078%

    No Known Activations