© 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. 17815
    Prev
    Next
    INDEX
    Explanations

    code file endings

    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
    -0.12
    çļĦä¸Ģå®ļ
    -0.08
    家å®Ŀ
    -0.07
    -0.07
    è§ī
    -0.06
    âĢİ
    -0.06
    Ľ
    -0.06
    ÃĤ
    -0.06
    çļĦè¿Ļç§į
    -0.06
    ÑģÑĤÑĥпление
    -0.06
    POSITIVE LOGITS
    æĭ±
    0.08
    utex
    0.07
    tij
    0.07
     elic
    0.07
    arul
    0.07
    åĨįåĪĽ
    0.06
    ÙĪاس
    0.06
    以æľįåĬ¡
    0.06
    THREAD
    0.06
    ../../../../
    0.06
    Activations Density 0.033%

    No Known Activations