© 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. 4104
    Prev
    Next
    INDEX
    Explanations

    violence, aggression, and physical harm

    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
    幸ç¦ıå¿«ä¹IJ
    -0.08
     frau
    -0.08
     Conspiracy
    -0.07
    èŃī
    -0.07
    òi
    -0.07
    hips
    -0.07
    à¸ģรà¸Ńà¸ĩ
    -0.07
     sog
    -0.07
    Navigator
    -0.07
    phans
    -0.07
    POSITIVE LOGITS
    æļ´åĬĽ
    0.14
     violence
    0.11
    æѦåĬĽ
    0.10
     escalation
    0.10
     Violence
    0.09
     Gewalt
    0.09
     physical
    0.09
    physical
    0.09
     intimidation
    0.09
    æļ´
    0.08
    Activations Density 0.090%

    No Known Activations