© 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. 34876
    Prev
    Next
    INDEX
    Explanations

    publisher Albert Ronald

    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
    æĪij好
    -0.08
    æ¯Ķè¾ĥ容æĺĵ
    -0.07
    à¹Ģà¸ģ
    -0.06
    说è¿ĩ
    -0.06
    оба
    -0.06
    è¿ĺæĺ¯ä¸į
    -0.06
     ...\
    -0.06
     famed
    -0.06
    /group
    -0.06
     Bela
    -0.06
    POSITIVE LOGITS
    ï¼ļ“
    0.08
    ï¼ļ"
    0.07
    ask
    0.07
    ä¼ģ
    0.07
    AccessType
    0.07
    ocy
    0.07
    ¥
    0.07
    asks
    0.07
    yed
    0.07
    -io
    0.06
    Activations Density 0.001%

    No Known Activations