© 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. 37460
    Prev
    Next
    INDEX
    Explanations

    numeric literals followed by operators

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.08
    fld
    -0.07
    psc
    -0.07
    _FALL
    -0.07
    cken
    -0.07
     Vigil
    -0.07
    ppen
    -0.07
    pel
    -0.06
     dahil
    -0.06
    ÙĨدÙĩ
    -0.06
    POSITIVE LOGITS
    ä¸į顺
    0.07
    顺
    0.07
    åĿļ
    0.07
    æ¶Ł
    0.07
    uggy
    0.07
    μαÏĦο
    0.06
    æ¯Ķè¾ĥæľī
    0.06
    æİ¥éĢģ
    0.06
    ra
    0.06
    ianya
    0.06
    Activations Density 0.018%

    No Known Activations