© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21639
    Prev
    Next
    INDEX
    Explanations

    economic and human impacts

    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
    ä¿ĥæĪIJ
    -0.07
    åĺĺ
    -0.07
     riform
    -0.07
    ç¨İåIJİ
    -0.07
    æ¯į鸡
    -0.07
    Ñĭл
    -0.07
    åĪĨæīĭ
    -0.06
    çĸij
    -0.06
    ä¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.06
     fria
    -0.06
    POSITIVE LOGITS
     livelihood
    0.08
    çļĦ人们
    0.08
    ä¸ĩ家
    0.08
    çݰ代åĮĸçļĦ
    0.08
    åıĹå½±åĵį
    0.08
    çĶŁåij½çº¿
    0.07
    çĵ¦å°Ķ
    0.07
    ocas
    0.07
     billions
    0.07
     infrastructure
    0.07
    Activations Density 0.136%

    No Known Activations