© 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. 665
    Prev
    Next
    INDEX
    Explanations

    mathematical series expansion

    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
    CLU
    -0.08
    第ä¸Ģ件äºĭ
    -0.07
    QUIT
    -0.07
    oglio
    -0.07
    VOKE
    -0.07
    å¾Ĺæīĭ
    -0.07
    erving
    -0.07
    Balancer
    -0.07
     kaps
    -0.07
    æ²ŁæĿij
    -0.07
    POSITIVE LOGITS
    çª
    0.08
    æĻ®
    0.07
    eze
    0.07
     Magnus
    0.07
     underestimate
    0.07
    ezo
    0.07
    kens
    0.06
     expansion
    0.06
     Ree
    0.06
    åIJ¸
    0.06
    Activations Density 0.003%

    No Known Activations