© 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. 27654
    Prev
    Next
    INDEX
    Explanations

    what is meant or referred to

    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
    è§Ī
    -0.08
    å°Ķå¾·
    -0.07
     overwhelmingly
    -0.07
    ä¸ĢæŀĿ
    -0.07
     neur
    -0.07
    imens
    -0.07
    ç»Ŀ大å¤ļæķ°
    -0.07
    odb
    -0.07
    erce
    -0.07
    éļĨéĩį举è¡Į
    -0.07
    POSITIVE LOGITS
     refers
    0.09
    æĮĩçļĦæĺ¯
    0.09
    æĮĩ
    0.09
    æĺ¯è¯´
    0.09
    æĺ¯æĮĩåľ¨
    0.09
    æĮĩçļĦ
    0.08
    å°±æĺ¯æĮĩ
    0.08
    æĺ¯æĮĩ
    0.07
    æĺ¯éĴĪ对
    0.07
    主è¦ģæĺ¯æĮĩ
    0.07
    Activations Density 0.007%

    No Known Activations