© 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. 30132
    Prev
    Next
    INDEX
    Explanations

    rules, policies, procedures, guidelines

    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
    _EXTRA
    -0.07
    为æĤ¨æݨèįIJ
    -0.07
    åİĨåı²ä¿¡æģ¯
    -0.07
    ysi
    -0.07
    pah
    -0.07
    chio
    -0.07
    å¦ĤæľŁ
    -0.07
    åĮºä½įä¼ĺåĬ¿
    -0.07
    igh
    -0.07
    _Display
    -0.07
    POSITIVE LOGITS
     rules
    0.16
     governing
    0.15
    /rules
    0.13
    è§ĦåĪĻåĴĮ
    0.13
    rules
    0.12
    è§ĦåĪĻ
    0.12
    è§Ħç«ł
    0.11
     пÑĢавила
    0.11
    åı¯å¾ª
    0.11
    è§Ħç«łåĪ¶åº¦
    0.11
    Activations Density 0.168%

    No Known Activations