© 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. 21017
    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
    AMED
    -0.08
    -China
    -0.08
    黯
    -0.08
    ANGAN
    -0.08
    ãģĦãģĭãģĮ
    -0.08
    ĸ
    -0.08
    ensp
    -0.08
    ToLeft
    -0.07
    æĹłå½±
    -0.07
    -registration
    -0.07
    POSITIVE LOGITS
    ohan
    0.07
    ris
    0.07
     cover
    0.06
     жизне
    0.06
    tempts
    0.06
    tw
    0.06
     z
    0.06
    _CONST
    0.06
     downs
    0.06
    鼷
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.