© 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. 60137
    Prev
    Next
    INDEX
    Explanations

    following titles/categories

    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
    clare
    -0.07
    åľ¨èģĮ
    -0.07
     Dise
    -0.07
    gres
    -0.07
    éĢłè°£
    -0.07
    ج
    -0.07
    att
    -0.07
    jum
    -0.06
    èĩªå·±çļĦå·¥ä½ľ
    -0.06
    ноÑģиÑĤ
    -0.06
    POSITIVE LOGITS
    ajak
    0.08
    ultipart
    0.07
    åIJij
    0.07
    ä¸Ģè¨Ģ
    0.06
    _abort
    0.06
    agerie
    0.06
    ä¸ĩåı¤
    0.06
    emens
    0.06
    طاء
    0.06
    è·ĭ
    0.06
    Activations Density 0.230%

    No Known Activations