© 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. 41352
    Prev
    Next
    INDEX
    Explanations

    those different understandings

    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
    standard
    -0.08
    æĺ¯ä¸Ģ个éĿŀ常
    -0.08
    åħ¶äºº
    -0.07
    vad
    -0.07
     MAT
    -0.07
    æ¨Ļæºĸ
    -0.07
    ä¸Ģå¼ı
    -0.07
     standard
    -0.07
     Standard
    -0.07
    emar
    -0.07
    POSITIVE LOGITS
    ç»ĵåIJĪèµ·æĿ¥
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ç»ĵåIJĪèĩªèº«
    0.07
    isca
    0.07
    尼奥
    0.07
    åıĬåħ¶å®ĥ
    0.07
    以åıĬåħ¶ä»ĸ
    0.07
    人æĹł
    0.07
    ç»ĦåIJĪ
    0.07
     conting
    0.07
    Activations Density 0.028%

    No Known Activations