© 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. 62762
    Prev
    Next
    INDEX
    Explanations

    extramarital affairs or cheating

    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
    igli
    -0.07
    é¦ĸæī¹
    -0.07
    isters
    -0.07
    é¥
    -0.06
     leaf
    -0.06
    _sibling
    -0.06
    onom
    -0.06
    ä¸Ģè¡Į人
    -0.06
    åĪĿåħ¥
    -0.06
    abol
    -0.06
    POSITIVE LOGITS
    æļ§æĺ§
    0.09
    éľ²æ°´
    0.09
    çİ°ä»»
    0.09
    åĩºè½¨
    0.08
    ä¸İåİŁ
    0.08
     adultery
    0.08
    æĪĸå¤ļ个
    0.08
    æĸ¬
    0.08
     openly
    0.08
    å¿łè¯ļ度
    0.08
    Activations Density 0.217%

    No Known Activations