© 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. 54970
    Prev
    Next
    INDEX
    Explanations

    citation ptr

    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
    untu
    -0.07
    身
    -0.07
    loat
    -0.07
    å
    -0.07
    å¥Ķ
    -0.07
    æµ®
    -0.06
    æĮīæ¯Ķä¾ĭ
    -0.06
    /Documents
    -0.06
    å¥Ī
    -0.06
    è¦
    -0.06
    POSITIVE LOGITS
     Cases
    0.08
    uids
    0.08
     cases
    0.07
    à¸İ
    0.07
     unanimous
    0.07
     decisions
    0.07
     appellate
    0.07
    éĢļæĬ¥äºĨ
    0.07
     supra
    0.07
    æľįåĬ¡åĴĮ
    0.07
    Activations Density 1.055%

    No Known Activations