© 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. 15572
    Prev
    Next
    INDEX
    Explanations

    questions and formulas

    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
    æīĢ以说
    -0.08
    clam
    -0.07
    çĦ¶
    -0.07
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    -0.07
    oller
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    -0.07
    æĮŁ
    -0.06
    iskas
    -0.06
    æ§Ľ
    -0.06
    agli
    -0.06
    POSITIVE LOGITS
    è¿Ļ个æĺ¯
    0.07
    é¦ĸåħĪ
    0.07
    è¿Ļæĺ¯ä¸Ģ个
    0.07
     Start
    0.06
     first
    0.06
    phis
    0.06
     start
    0.06
    озна
    0.06
    é¦ĸåħĪåľ¨
    0.06
    è¿Ļæĺ¯ä¸ª
    0.06
    Activations Density 0.015%

    No Known Activations