© 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. 9899
    Prev
    Next
    INDEX
    Explanations

    meaning of phrases

    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
    çī¹éĩĮ
    -0.07
    åĪĻåı¯
    -0.07
    jera
    -0.07
    nagy
    -0.07
    åħ¬è·¯å·¥ç¨ĭ
    -0.07
    anggapi
    -0.07
    повÑĸ
    -0.07
    dÃŃ
    -0.07
    SSI
    -0.07
    ollen
    -0.07
    POSITIVE LOGITS
    ãģ¨ãģĦãģĨæĦıåij³
    0.09
    æŁIJç§į
    0.09
     something
    0.08
     بÙħعÙĨÙī
    0.08
    aka
    0.08
    vs
    0.08
     olyan
    0.07
    çļĦæĦıæĢĿ
    0.07
    ä¸Ģç§į
    0.07
    ä¸ĭåIJĮ
    0.07
    Activations Density 0.040%

    No Known Activations