© 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. 59881
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diseases

    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
    onya
    -0.07
    èĩªåį«
    -0.06
    abort
    -0.06
    åĩł
    -0.06
    yun
    -0.06
    éªĮæĶ¶
    -0.06
     fin
    -0.06
     verst
    -0.06
    æ»ļ
    -0.06
    æĬķåħ¥
    -0.06
    POSITIVE LOGITS
    ianos
    0.09
     dugaan
    0.08
     longstanding
    0.08
    asta
    0.08
    çĶŁåīį
    0.08
    é¡½åĽº
    0.08
    ÑĢÑĥз
    0.08
     eligible
    0.07
    cach
    0.07
    é«ĺçĥŃ
    0.07
    Activations Density 1.380%

    No Known Activations