© 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. 37703
    Prev
    Next
    INDEX
    Explanations

    commodities and prices

    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
    æī«éĻ¤
    -0.07
    åīį人
    -0.06
    æįī
    -0.06
    èİĵ
    -0.06
    æĮģèĤ¡
    -0.06
    åIJĥä¸ľè¥¿
    -0.06
    举ä¸Ģåıįä¸ī
    -0.06
    åIJı
    -0.06
    ÙĦÙī
    -0.06
     spaced
    -0.05
    POSITIVE LOGITS
    产èĩª
    0.11
    ä¾ĽåºĶ
    0.10
    è´¨éĩı好
    0.10
     supply
    0.10
     اÙĦخاÙħ
    0.10
    -producing
    0.10
    ä¾Ľä¸įåºĶæ±Ĥ
    0.09
    éľĢæ±Ĥéĩı
    0.09
    产äºİ
    0.09
    çļĦéľĢæ±Ĥ
    0.09
    Activations Density 0.174%

    No Known Activations