© 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. 15365
    Prev
    Next
    INDEX
    Explanations

    code blocks or filenames

    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
    udes
    -0.07
    ÑĢово
    -0.07
    åĨķ
    -0.07
    rand
    -0.07
     kil
    -0.06
    olin
    -0.06
    è¿ĩåįĬ
    -0.06
    红ç³ĸ
    -0.06
    å¿ĥæĹ·ç¥ŀæĢ¡
    -0.06
    ä¼ı天
    -0.06
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀåij¢
    0.08
    ä¸įåħ¥
    0.08
    ä¸įä¿¡
    0.08
    ofi
    0.08
    æ°¸è¿ľ
    0.07
     Reject
    0.07
    éĢļéĢļ
    0.07
    onsin
    0.07
    è·Į
    0.07
    æĮ«
    0.07
    Activations Density 0.008%

    No Known Activations