© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15980
    Prev
    Next
    INDEX
    Explanations

    mathematical and code symbols

    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
    iter
    -0.07
    ITER
    -0.07
    丽èIJį
    -0.06
    otar
    -0.06
    udou
    -0.06
    ç¡®
    -0.06
    jung
    -0.06
    çłļ
    -0.06
    ersh
    -0.06
    åĽ¾æĸ¯
    -0.06
    POSITIVE LOGITS
    山人
    0.08
    æĭ¶
    0.07
    ayi
    0.07
     Ant
    0.07
    ä¸ĢåĬ¨
    0.07
    ï¼Ī
    0.07
    rave
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    Typed
    0.07
    ayout
    0.07
    Activations Density 0.003%

    No Known Activations