© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62816
    Prev
    Next
    INDEX
    Explanations

    center or point of reference

    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
    å®ļåŀĭ
    -0.08
    æ¿Ģå¢ŀ
    -0.07
    ä¸ĭæŀ¶
    -0.07
    éĵ¾æĿ¡
    -0.07
    katan
    -0.07
    TexImage
    -0.07
    ä¸ĬéĻIJ
    -0.07
    yim
    -0.07
    صÙĬÙĦ
    -0.07
    æķ²éŨ
    -0.07
    POSITIVE LOGITS
     center
    0.11
    -center
    0.11
    -centered
    0.10
    ä¸Ńå¿ĥçļĦ
    0.10
    center
    0.10
    为ä¸Ńå¿ĥ
    0.10
    ä¸Ńå¿ĥ
    0.10
    为ä¸Ńå¿ĥçļĦ
    0.10
    ä½įç½®
    0.10
     centre
    0.10
    Activations Density 0.015%

    No Known Activations