© 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. 46694
    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
    rd
    -0.08
    æĻĵæĺİ
    -0.07
    oule
    -0.07
    lsx
    -0.07
    .mockito
    -0.07
    nil
    -0.07
    rie
    -0.07
    åĭĻ
    -0.06
    lista
    -0.06
    PrototypeOf
    -0.06
    POSITIVE LOGITS
    bjerg
    0.08
    éĩıçļĦ
    0.08
     haber
    0.08
    å©
    0.08
    cop
    0.07
    .ident
    0.07
     ditem
    0.07
    ساء
    0.07
    çļĦä¸Ģæł·
    0.07
    åģ¥åĦ¿
    0.07
    Activations Density 0.000%

    No Known Activations