© 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. 30814
    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
    æį»
    -0.07
    ock
    -0.06
    überg
    -0.06
    endir
    -0.06
    =default
    -0.06
     Tutt
    -0.06
    ائÙĤ
    -0.06
    еÑīениÑı
    -0.06
    ara
    -0.06
    éĽĨä¸Ń
    -0.06
    POSITIVE LOGITS
    èį¼
    0.08
    abu
    0.08
    errs
    0.07
    عÙĦ
    0.07
    åĪ°çİ°åľ¨
    0.07
    ugas
    0.07
    REMOTE
    0.07
    ouro
    0.07
    è¡°
    0.07
    /GL
    0.07
    Activations Density 0.000%

    No Known Activations