© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 786
    Prev
    Next
    INDEX
    Explanations

    growth and synthesis processes

    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
    Negative Logits
    è¡¡
    -0.07
    åĪĨå¸ĥ
    -0.07
     beforehand
    -0.07
    失æķĪ
    -0.07
    Ñħов
    -0.07
    æķ£å¸ĥ
    -0.07
    ä¸įåIJĮç¨ĭ度
    -0.07
    bourne
    -0.06
    hw
    -0.06
     filtered
    -0.06
    POSITIVE LOGITS
     наÑĢаÑī
    0.10
     uninterrupted
    0.10
     пÑĢодолжаеÑĤÑģÑı
    0.09
     ë°©íĸ¥ìľ¼ë¡ľ
    0.09
     growth
    0.09
    è¿Ľå±ķæĥħåĨµ
    0.08
     ведеÑĤÑģÑı
    0.08
    åį´ä¸Ģ缴
    0.08
     Growth
    0.08
     attached
    0.08
    Activations Density 0.040%

    No Known Activations