© 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. 51825
    Prev
    Next
    INDEX
    Explanations

    usually done with or to

    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
    ibal
    -0.08
    ering
    -0.07
    наÑĤ
    -0.07
    ابد
    -0.06
    æľ¬è´¨ä¸Ĭ
    -0.06
    natal
    -0.06
    intos
    -0.06
    ëħĢ
    -0.06
     potentially
    -0.06
    agers
    -0.06
    POSITIVE LOGITS
     бÑĭваеÑĤ
    0.10
     usually
    0.09
     Ø¥Ùħا
    0.09
     often
    0.09
    มัà¸ģ
    0.09
     suele
    0.08
     suelen
    0.08
     menudo
    0.08
     Often
    0.08
     либо
    0.08
    Activations Density 0.034%

    No Known Activations