© 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. 61027
    Prev
    Next
    INDEX
    Explanations

    HTML `table` tags

    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
    urio
    -0.07
    andia
    -0.07
    anju
    -0.07
    å·¥åķĨä¸ļ
    -0.07
    åķ¬
    -0.07
    achel
    -0.06
    loh
    -0.06
    ostal
    -0.06
     Garrison
    -0.06
    为æĤ¨æݨèįIJ
    -0.06
    POSITIVE LOGITS
    æķ¦
    0.07
    åıªåı¯æĥľ
    0.07
    acar
    0.07
    à¸ģัà¸Ļà¹Ħà¸Ķà¹ī
    0.07
    å¸ĥéĩĮ
    0.06
    鼷æĸ¯
    0.06
     blame
    0.06
    ר×Ļ×ļ
    0.06
    	placeholder
    0.06
    vap
    0.06
    Activations Density 0.001%

    No Known Activations