© 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. 58959
    Prev
    Next
    INDEX
    Explanations

    academic reviews

    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
    Negative Logits
    æĹłä»¥
    -0.07
    alom
    -0.07
    æľīå¾Īå¤ļçļĦ
    -0.07
    å¾Ĺä¸įåģ¿
    -0.07
     GENERATED
    -0.07
    ä¸İä¸ĸçķĮ
    -0.07
    ocker
    -0.06
    _logging
    -0.06
    èĽ¹
    -0.06
    ụng
    -0.06
    POSITIVE LOGITS
    ?url
    0.07
    æĮ
    0.07
    .cgi
    0.07
    å¤įå·¥
    0.07
    éĩijåľ°
    0.07
    MQ
    0.07
    å¾¹åºķ
    0.06
    ffin
    0.06
    MediaPlayer
    0.06
    éĢıäºĨ
    0.06
    Activations Density 0.014%

    No Known Activations