© 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. 55723
    Prev
    Next
    INDEX
    Explanations

    combination or combining

    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
    rum
    -0.07
    彤
    -0.06
    åľ¨ä»ĬåIJİ
    -0.06
    åľ¨ä¸ĭ
    -0.06
    ä¸į计
    -0.06
    .Fixed
    -0.06
    á»ijc
    -0.06
    ÑħÑĤа
    -0.06
    izm
    -0.06
    åĩ¸
    -0.06
    POSITIVE LOGITS
     combines
    0.12
     combina
    0.12
     combine
    0.12
     combining
    0.12
     combination
    0.11
    combine
    0.11
     Combination
    0.11
    Combine
    0.11
    ç»ĦåIJĪ
    0.11
    ç»ĵåIJĪäºĨ
    0.11
    Activations Density 0.116%

    No Known Activations