© 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. 20154
    Prev
    Next
    INDEX
    Explanations

    email addresses and personal information

    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
    大å¤ļ
    -0.07
     gut
    -0.07
    è´«
    -0.06
    zd
    -0.06
    å¾Ĺå¿«
    -0.06
    å°½
    -0.06
    Ùħد
    -0.06
     اص
    -0.06
    åįĥ
    -0.06
    CP
    -0.06
    POSITIVE LOGITS
    继ç»ŃåĬªåĬĽ
    0.08
    istet
    0.08
    éĺħè¯»æľ¬æĸĩ
    0.08
    继ç»Ńåħ³æ³¨
    0.08
    ä¸ĭåIJĮ
    0.08
    agan
    0.07
    è¿Ļæł·çļĦä¸Ģ个
    0.07
    æѤè¡Į
    0.07
    æľªåľ¨
    0.07
     subsequent
    0.07
    Activations Density 0.002%

    No Known Activations