© 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. 58939
    Prev
    Next
    INDEX
    Explanations

    law and court document sections

    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
    accio
    -0.08
     UNION
    -0.07
    ç¿Ĵ
    -0.06
    åĪĨ级
    -0.06
    å±¹
    -0.06
    Inc
    -0.06
     promin
    -0.06
    èģĶåIJĪä¼ļ
    -0.06
    è¡Įä¸ļåıijå±ķ
    -0.06
    åĪĨåĪ«åľ¨
    -0.06
    POSITIVE LOGITS
    çīĪ
    0.08
    icial
    0.07
    Clr
    0.07
    brids
    0.07
    ilers
    0.07
    ฯ
    0.07
    iders
    0.07
    è²ī
    0.07
     Edition
    0.07
    .bi
    0.07
    Activations Density 0.165%

    No Known Activations