© 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. 23442
    Prev
    Next
    INDEX
    Explanations

    using or used followed by article or noun

    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
    ht
    -0.08
    æĢİæł·åģļ
    -0.07
    hte
    -0.06
    _hint
    -0.06
    åħ¶ä¸İ
    -0.06
    hti
    -0.06
    ulich
    -0.06
     singola
    -0.06
    ewnÄħ
    -0.06
    æīĢæľīåĨħ容
    -0.06
    POSITIVE LOGITS
    æľ¯è¯Ń
    0.10
    æ¯Ķåĸ»
    0.10
     terminology
    0.09
     language
    0.09
    形容
    0.09
     symbols
    0.08
     analogy
    0.08
    象å¾ģ
    0.08
    æĿ¥å½¢å®¹
    0.08
    çļĦè¯Ńè¨Ģ
    0.08
    Activations Density 0.060%

    No Known Activations