© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1851
    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
    ä¹īæĹłåıį顾
    -0.07
    ÏĢÏī
    -0.07
    èĮ¨
    -0.07
    ful
    -0.07
    serie
    -0.07
    ç±»çŃī
    -0.07
    зно
    -0.07
    æģ©æĸ¯
    -0.06
    /rem
    -0.06
    åĨħ侧
    -0.06
    POSITIVE LOGITS
    Ïĩε
    0.08
    евиÑĩ
    0.08
    cff
    0.07
    hav
    0.06
    евÑģкого
    0.06
    CDF
    0.06
    åįļè§Ī
    0.06
    cant
    0.06
    ãģĦãģıãĤī
    0.06
    æĻĹ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.