© 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. 60238
    Prev
    Next
    INDEX
    Explanations

    organizations and official bodies

    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
    ppure
    -0.09
    izzo
    -0.08
    åºĶæīĭ
    -0.08
    édération
    -0.08
    å§Ķæľĥ
    -0.07
    ulp
    -0.07
    aucoup
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    kish
    -0.07
    еÑĤо
    -0.07
    POSITIVE LOGITS
    æł¼
    0.06
    wig
    0.06
    æŀĿ
    0.06
    /
    0.06
    вÑijÑĢ
    0.06
    ä¹±æĸĹ
    0.05
    羿
    0.05
    l
    0.05
    人人
    0.05
    ä¸Ģä½ĵ
    0.05
    Activations Density 1.173%

    No Known Activations