© 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. 43539
    Prev
    Next
    INDEX
    Explanations

    possible outcomes

    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
    æĽ¾åĽł
    -0.08
    æĹ¢åı¯
    -0.08
    éľĸ
    -0.07
    MSN
    -0.07
    ��
    -0.07
    ë¯Ģë¡ľ
    -0.07
    åħ¶äºĮ
    -0.07
    æŶéľĢ
    -0.07
    åºĶåħĪ
    -0.07
    åĩłå£°
    -0.07
    POSITIVE LOGITS
    è¿ĩç¨ĭå½ĵä¸Ń
    0.11
    æĪĸèĢħæĺ¯
    0.10
    æĪĸèĢħ说
    0.10
    æ¯Ķå¦Ĥ说
    0.10
     somebody
    0.10
    åħ³äºİæĪij们
    0.10
     íĨµíķ´ìĦľ
    0.09
    æĪij们ä»Ĭ天
    0.09
     êµīìŀ¥íŀĪ
    0.09
     incredibly
    0.09
    Activations Density 0.252%

    No Known Activations