© 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. 740
    Prev
    Next
    INDEX
    Explanations

    APPEL/SUPPLEMENTARY

    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
    å§ij
    -0.08
    aturas
    -0.07
    æľ¬ç«ł
    -0.07
    kut
    -0.07
    thic
    -0.07
    åĻ©
    -0.06
    å¤ļ好
    -0.06
    cese
    -0.06
    eniu
    -0.06
    ERIC
    -0.06
    POSITIVE LOGITS
    ó
    0.06
    horn
    0.06
    à¸Ń
    0.06
    .hxx
    0.06
    æ¹ĸéĩĮ
    0.06
    rex
    0.06
    à¸ģล
    0.06
    ingg
    0.06
    idf
    0.06
    Rules
    0.06
    Activations Density 0.001%

    No Known Activations