© 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. 62815
    Prev
    Next
    INDEX
    Explanations

    honorable mention, algorithm, ties, leave

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    yai
    -0.07
     Äijá»ijt
    -0.07
    é¢ĦæľŁ
    -0.07
    ALE
    -0.07
     fod
    -0.07
     конвеÑĢ
    -0.07
     ene
    -0.07
    idot
    -0.07
    gae
    -0.07
    è¿ĻéĩĮæĺ¯
    -0.07
    POSITIVE LOGITS
     eventually
    0.08
    并æľĢç»Ī
    0.08
     Algorithm
    0.07
     precisely
    0.07
     algorithm
    0.07
    并被
    0.07
    æģ°å¥½
    0.07
    Algorithm
    0.07
     Cruc
    0.07
     ÑĢано
    0.07
    Activations Density 0.003%

    No Known Activations