© 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. 42186
    Prev
    Next
    INDEX
    Explanations

    swapping or exchange

    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
    монÑĤ
    -0.08
    çĸ²åĬĽ
    -0.08
    isman
    -0.08
    رÙĬد
    -0.08
    æĶ¾çŁ¢
    -0.08
     ÑģÑĥÑĤок
    -0.08
    erja
    -0.08
    passwd
    -0.08
    ems
    -0.08
    åıĬéħį件
    -0.08
    POSITIVE LOGITS
    aroo
    0.08
    ingly
    0.08
    orthy
    0.08
    åĬ¨çļĦ
    0.08
    /add
    0.07
    lock
    0.07
    èĩªå¦Ĥ
    0.07
     ngược
    0.07
    able
    0.06
    ster
    0.06
    Activations Density 0.016%

    No Known Activations