© 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. 45601
    Prev
    Next
    INDEX
    Explanations

    childhood stages

    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
    å£Ĭ
    -0.09
    ä¸ĭä¸ĢåĪ»
    -0.08
    å¨Ĩ
    -0.08
    æľĢä½İåѦåİĨ
    -0.07
    ä»İä»Ĭ天
    -0.07
     recently
    -0.07
    å¼łå»º
    -0.07
    两个å°ıæŶ
    -0.07
    æľĢæĸ°
    -0.07
     tonight
    -0.07
    POSITIVE LOGITS
     ìĭľìłĪ
    0.09
    hood
    0.09
    è®°äºĭ
    0.08
    æ¨¡æł·
    0.07
    å³¥åµĺ
    0.07
    壮å¿Ĺ
    0.07
    å¾Ģäºĭ
    0.07
     childhood
    0.07
    ç«¥åŃIJ
    0.06
    æĪIJåIJį
    0.06
    Activations Density 0.206%

    No Known Activations