© 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. 654
    Prev
    Next
    INDEX
    Explanations

    create law

    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
    еÑģÑĤв
    -0.08
    iac
    -0.07
    Reject
    -0.07
     purposely
    -0.07
    orientation
    -0.07
    jan
    -0.07
     deliberately
    -0.07
    anit
    -0.07
    _callbacks
    -0.07
     voluntarily
    -0.07
    POSITIVE LOGITS
    æĿĥéĻIJ
    0.10
    æİĪæĿĥ
    0.10
    ä¸įç»ı
    0.09
    æİĪæĿĥçļĦ
    0.09
     authority
    0.09
    ä¸ĭä¸Ģ级
    0.09
     authorized
    0.09
    æĵħèĩª
    0.08
     ê¶Įíķľ
    0.08
     authorization
    0.08
    Activations Density 0.022%

    No Known Activations