© 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. 17876
    Prev
    Next
    INDEX
    Explanations

    not all

    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
    tah
    -0.07
     almost
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
     hopefully
    -0.07
    gabe
    -0.07
    åŃ
    -0.07
    ä¸ĢèĪ¬ä¸įä¼ļ
    -0.07
     whichever
    -0.07
     whatever
    -0.07
     wherever
    -0.07
    POSITIVE LOGITS
    หรà¸Ńà¸ģ
    0.09
     nor
    0.09
     necessarily
    0.09
    ég
    0.08
     бÑĭваеÑĤ
    0.08
     lắm
    0.08
    ä¸Ģå¸Ĩé£İ顺
    0.08
    ä¹Łå¹¶éĿŀ
    0.08
    emuk
    0.08
    adang
    0.08
    Activations Density 0.089%

    No Known Activations