© 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. 44166
    Prev
    Next
    INDEX
    Explanations

    categories of things

    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¿Ļä¸ĢéĹ®é¢ĺ
    -0.09
    éĢĻé»ŀ
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
    è¿ĻçĤ¹
    -0.08
    å°±æĺ¯ä¸Ģç§į
    -0.08
    éĢĻä¸Ģé»ŀ
    -0.08
    æŁ¥çľĭæīĢæľī
    -0.08
    æĺ¯ä¸Ģ项
    -0.08
    igin
    -0.08
    æĺ¯ä¸Ģ个éĿŀ常
    -0.08
    POSITIVE LOGITS
    åIJĦèĩª
    0.16
     respectively
    0.16
    åIJĦèĩªçļĦ
    0.14
    ãģĿãĤĮãģŀãĤĮ
    0.13
     ê°ģê°ģ
    0.13
    约èĢĮåIJĮ
    0.12
     themselves
    0.12
    ä¹Łéĥ½æĺ¯
    0.12
    è¿ĻäºĽéĥ½æĺ¯
    0.12
    åIJĦæľī
    0.12
    Activations Density 0.334%

    No Known Activations