© 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. 28047
    Prev
    Next
    INDEX
    Explanations

    used for or to

    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
     usando
    -0.09
    à¸ģารà¹ĥà¸Ĭà¹ī
    -0.08
    åľ°ä½¿çĶ¨
    -0.08
     utilizando
    -0.08
    uso
    -0.08
    alet
    -0.08
     usage
    -0.08
    å·´å¡ŀ
    -0.08
    çĶ¨å¥½
    -0.08
     ÙĪإعادة
    -0.08
    POSITIVE LOGITS
     Äijá»ĥ
    0.09
     to
    0.08
    for
    0.08
    à¹ĥà¸Ļà¸ģาร
    0.08
     for
    0.08
    å¹²åĺĽ
    0.07
    对ä»ĺ
    0.07
    äºĨ对
    0.07
    strup
    0.07
     sparing
    0.07
    Activations Density 0.163%

    No Known Activations