© 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. 40470
    Prev
    Next
    INDEX
    Explanations

    Japanese suffixes like ãģ¯, ãĤī

    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
    ä¹ĭæīĢ以
    -0.09
    ãģĦãĤıãĤĨãĤĭ
    -0.08
    ä»Ģä¹Īåı«
    -0.07
    orum
    -0.07
    ogli
    -0.07
    clare
    -0.07
     ê·¸ëłĩëĭ¤ë©´
    -0.07
    Ùĭا
    -0.07
     ìĿ´ìłľëĬĶ
    -0.07
    ToLocal
    -0.07
    POSITIVE LOGITS
    ãģĺãĤģãģ¦
    0.15
    ãģ£ãģįãĤĬ
    0.11
     ë¬¼ë¡ł
    0.10
    ãģĺãĤģ
    0.08
    æŃ»çļĦ
    0.07
    ãĤĤãģ¡ãĤįãĤĵ
    0.07
    ãģķãģ¾
    0.07
    ãĤĤãģ®ãģ®
    0.07
    åı¯æĥ³
    0.07
    mane
    0.07
    Activations Density 0.006%

    No Known Activations