© 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. 10206
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operators

    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
    çī¹åĪ«æĺ¯åľ¨
    -0.07
    å°¤åħ¶åľ¨
    -0.07
    èĬ¬
    -0.07
    å°¤åħ¶æĺ¯åľ¨
    -0.06
    åĵªä¸ªå¥½
    -0.06
    STD
    -0.06
    æ·Ģ
    -0.06
    å¤įä¹łèµĦæĸĻ
    -0.06
    atori
    -0.06
    ä¹ŁåIJĮæł·
    -0.06
    POSITIVE LOGITS
    borough
    0.08
    ÃŃze
    0.08
    .jquery
    0.08
    ä¸įçĿĢ
    0.07
    иÑģÑĤÑĢа
    0.07
    å¤ŁäºĨ
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
    åħ¨åĭ¤
    0.07
    à¸ļรร
    0.07
    utas
    0.06
    Activations Density 0.012%

    No Known Activations