© 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. 56649
    Prev
    Next
    INDEX
    Explanations

    provide, keep, offers, spot, feature

    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»»ä½ķåħ¶ä»ĸ
    -0.07
     empl
    -0.07
    crast
    -0.07
     presently
    -0.07
    jami
    -0.07
    åºĥ
    -0.06
     apapun
    -0.06
    pras
    -0.06
     potentially
    -0.06
    ieso
    -0.06
    POSITIVE LOGITS
    ãģĹãģ¦ãģıãĤĮãģ¾ãģĻ
    0.08
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.08
    à¹ĥหà¹īà¹Ģรา
    0.07
    åľ¨ä»ĸ们çļĦ
    0.07
    èĩªå®¶çļĦ
    0.07
    èĩªå®¶
    0.07
    éĴĪ对ä¸įåIJĮ
    0.07
    çĶļèĩ³ä¼ļ
    0.07
    orton
    0.07
    æĪĸå¤ļæĪĸå°ij
    0.07
    Activations Density 0.227%

    No Known Activations