© 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. 50526
    Prev
    Next
    INDEX
    Explanations

    rules apply

    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
    Declared
    -0.08
     _______,
    -0.07
    åĽ½éĻħ社ä¼ļ
    -0.07
    ÙĢ
    -0.06
    ibera
    -0.06
    è¿Ļä¸įä»ħ
    -0.06
    .CV
    -0.06
    )':
    -0.06
    ’**
    -0.06
    大ä¸ĵåıĬ以ä¸ĬåѦåİĨ
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    åħ¶å®ĥ
    0.08
     ê·¸ëŁ¬íķľ
    0.07
    å¸ĮæľĽå¯¹å¤§å®¶
    0.07
     Teixeira
    0.06
    欢è¿İæĤ¨çļĦ
    0.06
    нок
    0.06
    ä¹ŁæĽ´åĬł
    0.06
    该类
    0.06
     weiterlesen
    0.06
    Activations Density 1.054%

    No Known Activations