© 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. 57303
    Prev
    Next
    INDEX
    Explanations

    sin, sinful, sins, forgiven, offenses

    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
    cott
    -0.09
    ndl
    -0.09
    ije
    -0.07
    IDI
    -0.07
    yata
    -0.07
    èĤ²æĪIJ
    -0.07
    ä¿ĿåĢ¼
    -0.07
    é¨
    -0.07
    umn
    -0.07
    å®ŀæĻ¯
    -0.07
    POSITIVE LOGITS
    æ¯Ķè¾ĥ严éĩį
    0.09
     sins
    0.09
    污
    0.08
     forgiven
    0.08
     offenses
    0.08
    Severity
    0.08
     severity
    0.08
    罪çļĦ
    0.08
    æ±ļãĤĮ
    0.08
    罪
    0.08
    Activations Density 0.023%

    No Known Activations