© 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. 19537
    Prev
    Next
    INDEX
    Explanations

    do/does/would questions

    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
    acular
    -0.07
    è¿ĻéĩĮæľī
    -0.06
    çĸij
    -0.06
    oster
    -0.06
    æľī许å¤ļ
    -0.05
    ä¸įä¼ļåĨį
    -0.05
    asm
    -0.05
    liness
    -0.05
    asan
    -0.05
    äºĨä¸ĢåįĬ
    -0.05
    POSITIVE LOGITS
     differs
    0.10
    缸æ¯Ķ
    0.10
     differ
    0.10
    缸æ¯Ķè¾ĥ
    0.09
     differed
    0.09
    à¸ļà¹īาà¸ĩ
    0.09
     differing
    0.09
     تختÙĦÙģ
    0.09
     különb
    0.08
    .Dispatcher
    0.08
    Activations Density 0.033%

    No Known Activations