© 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. 7553
    Prev
    Next
    INDEX
    Explanations

    threatening or violating rules

    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
     lap
    -0.08
     guide
    -0.07
     throughout
    -0.06
    åı¯ä»¥å¸®åĬ©ä½ł
    -0.06
     Deb
    -0.06
    -0.06
    lap
    -0.06
    cus
    -0.06
     successes
    -0.06
    ä¸įå®ļæľŁ
    -0.06
    POSITIVE LOGITS
    è¿ĿèĥĮ
    0.13
    è¿Ŀåıį
    0.12
    è¿ĿåıįäºĨ
    0.11
     violates
    0.10
     violating
    0.10
     violate
    0.10
     violation
    0.09
    è¿Ŀåıįä¸Ĭè¿°
    0.09
    æįŁ
    0.09
    æ»ĭ
    0.09
    Activations Density 0.090%

    No Known Activations