© 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. 51208
    Prev
    Next
    INDEX
    Explanations

    all this works

    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
    à¸ļาà¸ĩ
    -0.07
    åľ¨ä»»ä½ķ
    -0.07
     ALWAYS
    -0.07
    çļĦ两个
    -0.07
     always
    -0.07
    dsm
    -0.07
     лÑİбÑĭÑħ
    -0.07
    ä¹ĭäºĮ
    -0.07
    ä»»ä½ķæŶåĢĻ
    -0.07
     any
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪĩ
    0.10
     تÙĤرÙĬب
    0.10
    åĬłèµ·æĿ¥
    0.10
    æĪĸéĥ¨åĪĨ
    0.10
    è¿ĻäºĽéĥ½
    0.09
    uded
    0.09
    ergy
    0.09
    è¿ĻäºĽéĥ½æĺ¯
    0.08
    iance
    0.08
    çļĦä¸ĢåĪĩ
    0.08
    Activations Density 0.342%

    No Known Activations