© 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. 34979
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    rano
    -0.11
    skal
    -0.09
    opoulos
    -0.08
    astos
    -0.08
    euw
    -0.08
    еÑģе
    -0.08
    _MUTEX
    -0.08
    atis
    -0.08
    :frame
    -0.08
    cko
    -0.08
    POSITIVE LOGITS
    éĥ¨éŨ
    0.06
    ç¼ĸ
    0.06
    éĨį
    0.06
    åĭī
    0.06
    nowledge
    0.06
    çģĮ
    0.06
    ä»İä¸Ģ个
    0.06
    oh
    0.06
    acan
    0.06
     organ
    0.06
    Activations Density 0.000%

    No Known Activations