© 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. 800
    Prev
    Next
    INDEX
    Explanations

    fentanyl, patient, Buckley, chewing, first, gripping, one

    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
    esch
    -0.08
    åĬ
    -0.07
    idis
    -0.07
    æĺĤ
    -0.07
    åIJĦç§įéĹ®é¢ĺ
    -0.07
    yanto
    -0.07
    åĽĽä½į
    -0.07
    unga
    -0.07
    wann
    -0.07
    ulan
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.07
    论
    0.07
    æĹłæĦ§
    0.07
    illac
    0.07
    imat
    0.06
    Snippet
    0.06
    à¹ģà¸Ļà¹Īà¹ĥà¸Ī
    0.06
     istr
    0.06
    inders
    0.06
    æ¶Īæļij
    0.06
    Activations Density 0.001%

    No Known Activations