© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57244
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ken
    -0.08
    ming
    -0.07
    ito
    -0.06
    ÙĦد
    -0.06
    izo
    -0.06
    èĢĮä¸įè§ģ
    -0.06
    adies
    -0.06
    èĢĮéĿŀ
    -0.06
    æķĻäºİ
    -0.06
    ÙħÙĬ
    -0.06
    POSITIVE LOGITS
    çīĩåŃIJ
    0.08
    /embed
    0.08
    好æĸĩ
    0.07
    Ø®Ùħ
    0.07
    accio
    0.07
    å®
    0.07
    #
    0.07
    转转
    0.07
    å¨ĥ
    0.07
    éĢĽéĢĽ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.