© 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. 38390
    Prev
    Next
    INDEX
    Explanations

    image asset filename patterns

    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
    wach
    -0.07
     Mạc
    -0.07
    rown
    -0.07
    å¤ĸç§ijæīĭæľ¯
    -0.07
    sing
    -0.07
     Iterator
    -0.07
    æĹłäºĭ
    -0.07
     ÐĶона
    -0.07
    aise
    -0.07
    gor
    -0.07
    POSITIVE LOGITS
    opc
    0.07
    å¿ħå¡«
    0.06
    ä»Ģä¹ĪæĦıæĢĿ
    0.06
    æĢ»ç½²
    0.06
    verity
    0.06
    èģª
    0.06
    æѦç¥ŀ
    0.06
    ä¸įçŁ¥éģĵçļĦ
    0.06
     perms
    0.06
    매
    0.06
    Activations Density 0.236%

    No Known Activations