© 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. 37471
    Prev
    Next
    INDEX
    Explanations

    organizations and agencies

    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
    olean
    -0.07
    resso
    -0.07
    SYM
    -0.07
     Maggi
    -0.07
    )==
    -0.07
     bibir
    -0.07
     Chec
    -0.07
    rik
    -0.07
    ipay
    -0.07
    æķĻèĤ²è´¨éĩı
    -0.06
    POSITIVE LOGITS
    ëĮĢìĥģ
    0.07
    .getStyle
    0.07
    мок
    0.07
    áÄį
    0.07
    ä¼ĺéĢī
    0.06
    è¿ħ鼷
    0.06
    (commit
    0.06
    çĿĢä¸Ģ个
    0.06
     News
    0.06
     refs
    0.06
    Activations Density 0.268%

    No Known Activations