© 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. 4720
    Prev
    Next
    INDEX
    Explanations

    Hamiltonian

    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
    quÃŃ
    -0.06
    apar
    -0.06
    asar
    -0.06
     situ
    -0.06
    รุ
    -0.06
    ervlet
    -0.06
     regard
    -0.06
    åį³éĢĿ
    -0.06
    .lex
    -0.06
    pletion
    -0.06
    POSITIVE LOGITS
     incorporating
    0.09
    ushi
    0.08
    awa
    0.08
    aglio
    0.08
    etus
    0.08
     expression
    0.08
    å¼ı
    0.08
    ä¸įæĶ¾
    0.08
    ><![
    0.07
    они
    0.07
    Activations Density 0.027%

    No Known Activations