© 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. 57796
    Prev
    Next
    INDEX
    Explanations

    tax incentives, subsidies, credits

    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
    åıĹ人
    -0.07
    æ¯ı天éĥ½è¦ģ
    -0.07
    å°ĺ
    -0.07
    æŀIJ
    -0.06
    æ³¥çŁ³
    -0.06
    ä¸ĸçķĮåį«çĶŁç»Ħç»ĩ
    -0.06
    奴
    -0.06
     ASCII
    -0.06
    è´¡
    -0.06
    Slave
    -0.06
    POSITIVE LOGITS
    æī¶æĮģ
    0.14
    é¼ĵåĬ±
    0.13
    æī¶æĮģæĶ¿çŃĸ
    0.13
     subsidies
    0.13
    ä¼ĺæĥłæĶ¿çŃĸ
    0.12
     incentives
    0.12
     subsidy
    0.11
    é¼ĵåĭµ
    0.11
    æī¶
    0.11
    æĶ¯æĮģåĬĽåº¦
    0.11
    Activations Density 0.076%

    No Known Activations