© 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. 884
    Prev
    Next
    INDEX
    Explanations

    controlled

    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
    åIJĮ人
    -0.09
     Penc
    -0.07
     ÑĢаÑģпÑĢоÑģÑĤ
    -0.07
    idere
    -0.07
     ÑĢозÑĭ
    -0.07
    严éĩį
    -0.07
    ä¸įè§ģäºĨ
    -0.07
     Duarte
    -0.07
    åĽłä¸ºæľīäºĨ
    -0.06
     Aner
    -0.06
    POSITIVE LOGITS
     controlled
    0.13
    -controlled
    0.13
    æݧåĪ¶çļĦ
    0.13
    controlled
    0.13
    æĿ¥æݧåĪ¶
    0.12
     controlling
    0.12
    åı¯æݧ
    0.12
    è°ĥèĬĤ
    0.12
     adjustable
    0.12
     control
    0.11
    Activations Density 0.204%

    No Known Activations