© 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. 64664
    Prev
    Next
    INDEX
    Explanations

    summary and recap

    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
    rud
    -0.07
    详ç»ĨåĨħ容
    -0.06
    stras
    -0.06
    anka
    -0.06
    ois
    -0.06
    ç»Ĩå¿ĥ
    -0.06
    åħĪè¿Ľ
    -0.06
    ä¸į好
    -0.06
    详æĥħ
    -0.06
    lec
    -0.06
    POSITIVE LOGITS
    æĢ»ç»ĵ
    0.14
     summarize
    0.13
    summary
    0.13
    總çµIJ
    0.12
    æĢ»ç»ĵåĴĮ
    0.12
     summary
    0.11
     recap
    0.11
    æĢ»ç»ĵä¸Ģä¸ĭ
    0.11
    _summary
    0.11
     summarizes
    0.11
    Activations Density 0.039%

    No Known Activations