© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52104
    Prev
    Next
    INDEX
    Explanations

    Module, holder, Notification, Choices, Outlook, Plus

    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
    Negative Logits
    çĸ¥
    -0.07
    cardo
    -0.07
    erna
    -0.07
    æĪĸ以
    -0.06
    unto
    -0.06
    wohl
    -0.06
    ä¸ĭæīĭ
    -0.06
    idth
    -0.06
    åĪ°å¤©
    -0.06
    çĴŀ
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĬł
    0.08
     aka
    0.07
    åĴĮéĹ®é¢ĺ
    0.07
    лей
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    æ¯ıåIJį
    0.07
     вза
    0.07
    overlap
    0.07
    ORIZATION
    0.07
    ä¸İæݧåĪ¶
    0.07
    Activations Density 0.255%

    No Known Activations