© 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. 7613
    Prev
    Next
    INDEX
    Explanations

    Here's a quick sketch

    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
    è¿ĻæĿ¡è·¯
    -0.09
    ÙĬÙĬر
    -0.07
    æĭŃ缮
    -0.07
    è¿Ļç§įæĸ¹æ³ķ
    -0.07
    å¤ļè¿ľ
    -0.07
    è¿ĺä¼ļåĩºçİ°
    -0.07
    è¶ĭåIJij
    -0.07
    kos
    -0.07
    åIJĮæŶè¿ĺè¦ģ
    -0.07
    è¶Ł
    -0.07
    POSITIVE LOGITS
    am
    0.08
     bref
    0.07
     Facts
    0.07
     facts
    0.06
    apult
    0.06
    ä¸ŀ
    0.06
    ç¿Ķ
    0.06
     Jep
    0.06
    ç®Ģè¦ģ
    0.06
    ç®ĢçŁŃ
    0.06
    Activations Density 0.040%

    No Known Activations