© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55012
    Prev
    Next
    INDEX
    Explanations

    forms of abuse or severity

    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
    Negative Logits
     controversial
    -0.08
    æĪijçļĦç¥Ŀç¦ı
    -0.08
    stro
    -0.08
     polém
    -0.07
    ablish
    -0.07
     contentious
    -0.07
    XmlAttribute
    -0.07
    çĸijä¼¼è¿Ŀè§Ħ
    -0.07
    odd
    -0.07
    çĽİ
    -0.07
    POSITIVE LOGITS
     severity
    0.14
     Severity
    0.13
    Severity
    0.12
    severity
    0.12
     inflicted
    0.12
     worse
    0.12
    รุà¸Ļà¹ģรà¸ĩ
    0.11
    严éĩįç¨ĭ度
    0.11
     inflict
    0.10
     caused
    0.10
    Activations Density 0.607%

    No Known Activations