© 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. 23290
    Prev
    Next
    INDEX
    Explanations

    new, follow-up, output, post, warped

    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
     lẻ
    -0.08
    ingat
    -0.07
    ลิ
    -0.07
    edly
    -0.07
    å¾ĪæĹ©
    -0.06
    /lg
    -0.06
    éķ¿æľŁä»¥æĿ¥
    -0.06
    ÏĢη
    -0.06
    å¾ĪæĹ©å°±
    -0.06
    è¶Ĭ
    -0.06
    POSITIVE LOGITS
    ,new
    0.11
    æĸ°çļĦ
    0.11
    (new
    0.10
    çŃīæĸ°
    0.10
    åľ¨æĸ°çļĦ
    0.10
     new
    0.10
     ìĥĪë¡ľìļ´
    0.09
    =new
    0.09
    æĸ°ãģĹãģĦ
    0.09
    ä¸İåİŁ
    0.09
    Activations Density 0.054%

    No Known Activations