© 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. 32897
    Prev
    Next
    INDEX
    Explanations

    within

    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
    nese
    -0.06
    кин
    -0.06
     sparing
    -0.06
    edo
    -0.06
    éĢļ天
    -0.06
    endo
    -0.06
    edd
    -0.06
    è¼Ķ
    -0.06
     mutual
    -0.06
    è¾ħ
    -0.06
    POSITIVE LOGITS
    åľ¨æ¯ı个
    0.11
    æ¯ıç»Ħ
    0.11
    within
    0.11
    à¹ĥà¸Ļà¹ģà¸ķà¹Īละ
    0.10
    Within
    0.10
     Within
    0.09
    æįĨç»ij
    0.09
     within
    0.09
    å½ĵåľ°çļĦ
    0.09
    _within
    0.09
    Activations Density 0.240%

    No Known Activations