© 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. 21400
    Prev
    Next
    INDEX
    Explanations

    exchange, replacement, swap

    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
    建åħļ
    -0.07
     contrib
    -0.07
    æij§
    -0.06
     contributes
    -0.06
    å®£ä¼łæķĻèĤ²
    -0.06
     contributing
    -0.06
    åĢįå¢ŀ
    -0.06
     Om
    -0.06
    ray
    -0.06
    join
    -0.06
    POSITIVE LOGITS
    ç½®æį¢
    0.17
    交æį¢
    0.17
     exchange
    0.15
    æĽ¿æį¢
    0.15
     swap
    0.15
    Swap
    0.15
     exchanging
    0.15
    äºĴæį¢
    0.14
     exchanged
    0.14
    swap
    0.14
    Activations Density 0.015%

    No Known Activations