© 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. 12227
    Prev
    Next
    INDEX
    Explanations

    adolescent, teens

    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
    éĥ½æĺ¯ä¸ĢäºĽ
    -0.08
    åŁ¹åħ»å¹¼åĦ¿
    -0.07
     Babies
    -0.07
    มูล
    -0.07
    åĦ¿æŶ
    -0.07
     bebés
    -0.07
    óp
    -0.07
     bebé
    -0.07
    assen
    -0.07
    æµĨ
    -0.07
    POSITIVE LOGITS
    çīĪçļĦ
    0.08
    å°ıä¼Ļ
    0.08
     подÑĢоÑģÑĤ
    0.08
     teens
    0.08
     Adolesc
    0.08
    -aged
    0.08
    åıĬ家éķ¿
    0.08
     вÑģÑĤÑĥпа
    0.07
    åıĽéĢĨ
    0.07
    æĹ¶æľŁ
    0.07
    Activations Density 0.116%

    No Known Activations