© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62379
    Prev
    Next
    INDEX
    Explanations

    avoid, dismiss, hide, ignore, cancel

    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
    .align
    -0.08
    é¼ĵèĪŀ
    -0.07
     aff
    -0.07
    kaan
    -0.07
    çĭ
    -0.07
    æ¿ĢåıijäºĨ
    -0.06
    ãģĮãĤĭ
    -0.06
     Gru
    -0.06
    fer
    -0.06
     cop
    -0.06
    POSITIVE LOGITS
     deaktiv
    0.10
    åIJ¦å®ļ
    0.10
    ä¸įä¸Ĭ
    0.10
    æĿľç»Ŀ
    0.10
     عدÙħ
    0.10
    .removeItem
    0.09
     بعدÙħ
    0.09
     excludes
    0.09
     verzichten
    0.09
    ä¸įåıĤä¸İ
    0.09
    Activations Density 0.355%

    No Known Activations