© 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. 40226
    Prev
    Next
    INDEX
    Explanations

    general 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
    astia
    -0.08
    ลุ
    -0.07
    æĢ»ä½ĵè¦ģæ±Ĥ
    -0.07
    ÑĢÑĤе
    -0.07
    alej
    -0.07
    ×Ĺ×Ļ×Ŀ
    -0.07
    dff
    -0.07
    vÄĥ
    -0.06
    è·¯éĢı
    -0.06
    /shop
    -0.06
    POSITIVE LOGITS
    vey
    0.08
    ä½ķ为
    0.07
    stad
    0.07
    æīĢè°ĵ
    0.07
    ÏĢει
    0.06
    oe
    0.06
    丽ä¸Ŀ
    0.06
    notated
    0.06
    ä¸ĭåIJĮ
    0.06
    stance
    0.06
    Activations Density 0.318%

    No Known Activations