© 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. 47311
    Prev
    Next
    INDEX
    Explanations

    . or -even

    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
     somehow
    -0.08
    æŁIJç§į
    -0.07
    ä½Ĩè¿Ļ
    -0.07
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.07
     (?)
    -0.07
    eme
    -0.06
    áf
    -0.06
    ä¼¼ä¹İ
    -0.06
    æłĹ
    -0.06
    à¸ļà¹īาà¸ĩ
    -0.06
    POSITIVE LOGITS
    æĽ´ä½ķåĨµ
    0.09
    åį³ä½¿
    0.08
     even
    0.08
    åį³ä¾¿
    0.08
    èĢĮä¸Ķæĺ¯
    0.08
    -even
    0.08
     dù
    0.08
    åį³ä½¿åľ¨
    0.08
    even
    0.08
    åĨµä¸Ķ
    0.08
    Activations Density 0.005%

    No Known Activations