© 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. 870
    Prev
    Next
    INDEX
    Explanations

    how things work or happen

    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
    为äºĨ满足
    -0.07
    åħ¬å¼ĢçļĦ
    -0.06
    è¡į
    -0.06
     forsk
    -0.06
    æ¼Ĥ
    -0.06
     naive
    -0.06
    å³Ń
    -0.06
    åĸĦ
    -0.06
     anthrop
    -0.06
     bursting
    -0.06
    POSITIVE LOGITS
    æģ¢å¤įæŃ£å¸¸
    0.11
    æŃ£å¸¸
    0.11
    æŃ£å¸¸çļĦ
    0.11
    æĺ¯åIJ¦æŃ£å¸¸
    0.11
    ä¸įæŃ£å¸¸
    0.10
    IVEN
    0.09
     normal
    0.09
    Normal
    0.09
    æŃ£å¸¸æĥħåĨµä¸ĭ
    0.09
     normale
    0.09
    Activations Density 0.404%

    No Known Activations