© 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. 41287
    Prev
    Next
    INDEX
    Explanations

    discrimination based on race, religion, disability, affiliation

    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
    archive
    -0.08
    voer
    -0.08
    -archive
    -0.07
    iena
    -0.07
    åĪ©çī©
    -0.07
    :{}
    -0.07
    apes
    -0.07
    aight
    -0.07
    ä¸įå°ijçļĦ
    -0.07
    åĴĮå¿«ä¹IJ
    -0.06
    POSITIVE LOGITS
    æµĭè¯ķç»ĵæŀľ
    0.09
     unrelated
    0.09
     religion
    0.08
     disability
    0.08
     ethnicity
    0.08
     nationality
    0.07
    æĹłåħ³
    0.07
     whim
    0.07
    è¿·ä¿¡
    0.07
     affiliation
    0.07
    Activations Density 0.051%

    No Known Activations