© 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. 59993
    Prev
    Next
    INDEX
    Explanations

    retaliation and reprisal actions

    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
    èѦåĬĽ
    -0.07
    è¶ģ
    -0.07
    äºī
    -0.07
     عاج
    -0.07
    ä¹ĺ
    -0.06
    imports
    -0.06
    è¿«åĪĩ
    -0.06
    allocate
    -0.06
    èµĺ
    -0.06
    å¾·æĸ¯
    -0.06
    POSITIVE LOGITS
     immunity
    0.09
     protected
    0.09
    æĹłçķı
    0.09
    çļĦä¿ĿæĬ¤
    0.09
    Protected
    0.09
     dám
    0.09
     brav
    0.09
    人身å®īåħ¨
    0.09
    åħįåıĹ
    0.08
     geschützt
    0.08
    Activations Density 0.116%

    No Known Activations