© 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. 51981
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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
    åĽĽä¸ªæĸ¹éĿ¢
    -0.07
    ïs
    -0.07
    addle
    -0.07
    åĽ½éŨ
    -0.07
    åľ¨å¹³æŶ
    -0.07
    æ®´
    -0.07
    inar
    -0.07
    mah
    -0.07
    次äºİ
    -0.07
     Hit
    -0.07
    POSITIVE LOGITS
    olling
    0.09
     testers
    0.07
    elis
    0.07
    楽
    0.07
    çīĽè§Ĵ
    0.07
    -vars
    0.07
    é¡»çŁ¥
    0.07
    oose
    0.07
    ijnen
    0.06
    °
    0.06
    Activations Density 0.001%

    No Known Activations