© 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. 55251
    Prev
    Next
    INDEX
    Explanations

    mechanism of

    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
    orno
    -0.08
    ehme
    -0.08
     اÙĦÙħدÙī
    -0.07
    à¹Ģà¸Ĺียม
    -0.07
    åŁºä¸ļ
    -0.07
    owed
    -0.07
    kaar
    -0.07
    enburg
    -0.07
    enso
    -0.07
     sekal
    -0.07
    POSITIVE LOGITS
    atically
    0.10
    ically
    0.08
    ologies
    0.08
    ipse
    0.08
    ily
    0.08
    umbo
    0.08
    ãģĺãĤģãģ¦
    0.08
    /process
    0.08
    à¸ļาà¸ĩà¸Ńยà¹Īาà¸ĩ
    0.08
    ysterious
    0.07
    Activations Density 0.038%

    No Known Activations