© 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. 55435
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation or "I"

    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
     Bray
    -0.07
    azzi
    -0.07
    åħįå¾Ĺ
    -0.06
    颤æĬĸ
    -0.06
    lene
    -0.06
    é¦ĸåħĪæĺ¯
    -0.06
    uda
    -0.06
    该æľīçļĦ
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
    æ¯ĶæĪij们
    -0.06
    POSITIVE LOGITS
     now
    0.11
     ÑĤепеÑĢÑĮ
    0.11
    çİ°åľ¨çľĭæĿ¥
    0.11
    .Now
    0.09
     ìĿ´ìłľ
    0.08
    now
    0.08
     ahora
    0.08
     ÅŁimdi
    0.08
     agora
    0.08
     Now
    0.08
    Activations Density 0.081%

    No Known Activations