© 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. 21272
    Prev
    Next
    INDEX
    Explanations

    Chrome, Firefox

    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
    naan
    -0.08
    æĩ
    -0.07
    æĹ·
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    ATS
    -0.07
    åıįä¹ĭ
    -0.07
    漫
    -0.07
     Ston
    -0.07
    esto
    -0.07
    ä¸įäºĨäºĨ
    -0.07
    POSITIVE LOGITS
    åħ¨å¤©
    0.08
    éĽ¯
    0.08
    ä¸įåĪĨ
    0.08
    åıªæľīä¸Ģ个
    0.07
    .NewReader
    0.07
    åįķä¸ĢçļĦ
    0.07
    lis
    0.07
    åįķä¸Ģ
    0.07
    uga
    0.07
    always
    0.07
    Activations Density 0.246%

    No Known Activations