© 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. 13599
    Prev
    Next
    INDEX
    Explanations

    for you to

    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
    éĩij森
    -0.07
    å°Ķ
    -0.07
    æľ¬ç¯ĩæĸĩç«ł
    -0.06
    icule
    -0.06
    รà¸ģ
    -0.06
    å¸ĥä»Ģ
    -0.06
    RK
    -0.06
     Quinta
    -0.06
    rak
    -0.06
    å°Ķåħĭ
    -0.06
    POSITIVE LOGITS
    对æѤ
    0.21
    对è¿ĻäºĽ
    0.18
    åľ¨è¿Ļæĸ¹éĿ¢
    0.18
    çļĦè¿Ļç§į
    0.18
    è¿Ļæĸ¹éĿ¢çļĦ
    0.17
    å°įæѤ
    0.17
    å°Ĩè¿ĻäºĽ
    0.16
    æĬĬè¿ĻäºĽ
    0.15
    ä¸İæѤ
    0.15
    çļĦè¿Ļä¸Ģ
    0.15
    Activations Density 0.519%

    No Known Activations