© 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. 38054
    Prev
    Next
    INDEX
    Explanations

    refer 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
    Ó©
    -0.07
    妥åĸĦä¿Ŀ管
    -0.07
    Ø´Ùģ
    -0.07
    大纲
    -0.07
    ä¸Ģèµ·åģļ
    -0.07
    éĩijå±±éĵ¶å±±
    -0.07
    callbacks
    -0.07
    -0.06
    妥åĸĦ
    -0.06
    åºĶ该ä¸įä¼ļ
    -0.06
    POSITIVE LOGITS
    åIJĮåIJį
    0.15
    æĦıä¹īä¸ĬçļĦ
    0.10
    ä¹Łåı«
    0.08
     synonymous
    0.08
     meanings
    0.08
    两å±Ĥ
    0.08
     unrelated
    0.08
    ä¹ĭåIJį
    0.08
     meaning
    0.07
     synonyms
    0.07
    Activations Density 0.673%

    No Known Activations