© 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. 51750
    Prev
    Next
    INDEX
    Explanations

    childhood personality traits preceding adulthood

    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
    æĪªèĩ³
    -0.08
    erson
    -0.08
    æļ§
    -0.07
    βε
    -0.07
    rick
    -0.07
    еÑģÑĤв
    -0.06
     lately
    -0.06
     Maggi
    -0.06
    ä»Ĭå¹´ä¸ĬåįĬå¹´
    -0.06
    aria
    -0.06
    POSITIVE LOGITS
     onwards
    0.10
     onward
    0.09
    åĴĮæľªæĿ¥
    0.09
     nanti
    0.09
    æľŁçļĦ
    0.08
    缴æİ¥åIJij
    0.07
    è¿ĩåIJİ
    0.07
    åĴĮåīį
    0.07
    -era
    0.07
    è¶
    0.07
    Activations Density 0.026%

    No Known Activations