© 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. 61147
    Prev
    Next
    INDEX
    Explanations

    enumerated list items

    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
    æłĩåĩĨä¿¡æģ¯
    -0.08
    ä»ĸ身ä¸Ĭ
    -0.08
    æĸ°éĹ»å®¢æĪ·ç«¯
    -0.07
    Profiler
    -0.07
    erma
    -0.07
    å¾ĭå¸ĪäºĭåĬ¡æīĢå¾ĭå¸Ī
    -0.07
    çŃīç´ļ
    -0.07
    Ĩµ
    -0.07
    çŃī级
    -0.07
    _repr
    -0.07
    POSITIVE LOGITS
     sub
    0.06
    为ä¾Ŀæį®
    0.06
     indirect
    0.06
    b
    0.06
    ipes
    0.06
    çĿĽ
    0.06
    c
    0.06
     phrase
    0.06
    cie
    0.06
    é¾ĻåŁİ
    0.06
    Activations Density 0.041%

    No Known Activations