© 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. 39882
    Prev
    Next
    INDEX
    Explanations

    amendment or studies

    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
    ÙĪاع
    -0.08
    elpers
    -0.08
    使ãģĦæĸ¹
    -0.08
    ìĨĮëĬĶ
    -0.07
    enska
    -0.07
    udian
    -0.07
    _;
    -0.07
     fabr
    -0.07
    æĺ¯ä¸ĢåĪĩ
    -0.07
    éĩįçĤ¹æĺ¯
    -0.07
    POSITIVE LOGITS
    羣å®ŀæĢ§è´Łè´£
    0.11
    åĨħå®¹è¿Ľè¡Į
    0.09
    éĹ®é¢ĺè¿Ľè¡Į
    0.09
    æķ°æį®è¿Ľè¡Į
    0.09
    çļĦä¸ĢåĪĩéĥ½
    0.09
    ä¿¡æģ¯è¿Ľè¡Į
    0.09
    å·¥ä½ľè¿Ľè¡Į
    0.08
    æĥħåĨµè¿Ľè¡Į
    0.08
    æĸ¹å¼ıè¿Ľè¡Į
    0.08
    设å¤ĩè¿Ľè¡Į
    0.08
    Activations Density 0.023%

    No Known Activations