© 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. 13216
    Prev
    Next
    INDEX
    Explanations

    python file headers

    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
    ä¸ĵæłı
    -0.08
     disg
    -0.07
    pped
    -0.07
     СкаÑĩаÑĤÑĮ
    -0.07
    çļĦä¸ĵæłı
    -0.07
    делÑĮ
    -0.07
    .ie
    -0.07
    ned
    -0.07
    éĿŀæłĩ
    -0.07
    éĽ·é¸£
    -0.07
    POSITIVE LOGITS
     student
    0.07
    人ä¸Ģ
    0.07
    bst
    0.07
     tuition
    0.07
    请åIJĮåѦ们
    0.07
    essi
    0.06
    课å¤ĸ
    0.06
    å¸ĮæľĽä½ł
    0.06
    _student
    0.06
    èį¡
    0.06
    Activations Density 0.156%

    No Known Activations