© 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. 51931
    Prev
    Next
    INDEX
    Explanations

    welcome and introductions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ulence
    -0.07
    oyo
    -0.07
    жели
    -0.06
    ×Ļק
    -0.06
    водÑĭ
    -0.06
    æĶ¯
    -0.06
     driven
    -0.06
     control
    -0.06
     конÑĤÑĢолÑı
    -0.06
    æݧåĪ¶çļĦ
    -0.06
    POSITIVE LOGITS
    /welcome
    0.13
     welcoming
    0.10
    ductory
    0.10
    æĸ°æľĭåıĭ
    0.10
    欢è¿İ
    0.10
     знаком
    0.09
     warmly
    0.09
    欢è¿İåħī临
    0.09
     welcomed
    0.09
    æīĵæĭĽåij¼
    0.09
    Activations Density 0.218%

    No Known Activations