© 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. 42207
    Prev
    Next
    INDEX
    Explanations

    large N approximations

    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
    ç«¥åŃIJ
    -0.07
     accumulated
    -0.07
    thal
    -0.06
    yped
    -0.06
    ×ľ×ª
    -0.06
     accum
    -0.06
    ãĥŃãĥ¼ãĤº
    -0.06
     covers
    -0.06
    continuous
    -0.06
    liest
    -0.06
    POSITIVE LOGITS
     Dalla
    0.08
    çī¢
    0.07
    ç¥ĸ
    0.07
    zahl
    0.07
    åĩºèµĦæĸ¹å¼ı
    0.07
    ç§ĺ
    0.07
    æķ°ä¸º
    0.07
     szám
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
     dicon
    0.07
    Activations Density 0.002%

    No Known Activations