© 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. 50845
    Prev
    Next
    INDEX
    Explanations

    crimes against humanity

    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
    oc
    -0.06
    ç»ıæµİ
    -0.06
    an
    -0.06
    ç»ĥä¹ł
    -0.06
    akah
    -0.06
     function
    -0.06
    ana
    -0.06
    Br
    -0.06
     \
    -0.05
    Sport
    -0.05
    POSITIVE LOGITS
    ÙģÙĪ
    0.09
    ophys
    0.09
    spur
    0.09
    IRM
    0.09
    åĩĿå¿ĥ
    0.09
    eggia
    0.09
     дока
    0.08
     Сви
    0.08
    itmen
    0.08
    cheng
    0.08
    Activations Density 0.001%

    No Known Activations