© 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. 52148
    Prev
    Next
    INDEX
    Explanations

    criminal law

    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
    ÙĬرة
    -0.09
    परà¥į
    -0.08
    кÑĢÑĭ
    -0.08
    å©Ĩ
    -0.08
    кладÑĭ
    -0.08
    вÑĸÑĢ
    -0.08
    HOLDER
    -0.08
    çŃĭèĨľ
    -0.08
    guas
    -0.08
    prites
    -0.08
    POSITIVE LOGITS
     Nack
    0.07
    åĴĮ社åĮº
    0.07
    ation
    0.07
    oad
    0.07
    itary
    0.07
    jed
    0.06
    åħ¥ä¼į
    0.06
    ized
    0.06
    ÄĻc
    0.06
     twilight
    0.06
    Activations Density 0.019%

    No Known Activations