© 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. 40714
    Prev
    Next
    INDEX
    Explanations

    question about code

    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
    åĽłæŃ¤åľ¨
    -0.08
    ÑĩиÑģ
    -0.08
    à®±à¯įà®±
    -0.07
    olet
    -0.07
    .utf
    -0.07
     derfor
    -0.07
    æľīå½¢
    -0.07
    um
    -0.07
    ither
    -0.07
    -Cal
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¼ļ
    0.07
    åĩºçİ°çļĦéĹ®é¢ĺ
    0.06
    åĵªéĩĮ
    0.06
    iped
    0.06
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.06
    çļĦä¸ĢäºĽ
    0.06
    éľĢè¦ģ注æĦı
    0.06
    è±Ĩ
    0.06
    æĪijåIJĹ
    0.06
    æµĭè¯ķ
    0.06
    Activations Density 0.017%

    No Known Activations