© 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. 37778
    Prev
    Next
    INDEX
    Explanations

    asymmetric or unequal relationships

    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
    æĮ¯
    -0.07
    Encoded
    -0.07
    éĹŃ
    -0.06
    çļĦåħ¨
    -0.06
    大åħ¸
    -0.06
    .Mapping
    -0.06
     Encyclopedia
    -0.06
     entirety
    -0.06
    ç»ĵ
    -0.06
     enc
    -0.06
    POSITIVE LOGITS
    ä¸į对称
    0.13
     asym
    0.13
     asymmetric
    0.13
    ä¸į平衡
    0.10
     unequal
    0.09
    ä¸įå¹³
    0.09
    æĤ¬æ®Ĭ
    0.09
    (single
    0.09
    æ··åIJĪåŀĭ
    0.09
     hybrid
    0.08
    Activations Density 0.102%

    No Known Activations