© 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. 19722
    Prev
    Next
    INDEX
    Explanations

    closing tags or quotes

    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
    ersh
    -0.10
    åı«åģļ
    -0.08
    ught
    -0.07
    hares
    -0.07
    åIJįåı«
    -0.07
     Bekannt
    -0.07
    æīĵè¿ĩ
    -0.07
    称为
    -0.07
    çľº
    -0.07
    è·
    -0.07
    POSITIVE LOGITS
    ä¸Ģè¯į
    0.11
    è¿Ļ个è¯į
    0.10
    äºĮåŃĹ
    0.09
    åŃĹæł·
    0.07
    åŃĹçľ¼
    0.07
    ingos
    0.07
    åĽĽä¸ªåŃĹ
    0.07
    è¿Ļ个åIJįåŃĹ
    0.07
    onyms
    0.07
    æĪĸåħ¶
    0.07
    Activations Density 0.108%

    No Known Activations