© 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. 7213
    Prev
    Next
    INDEX
    Explanations

    convenient or example

    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
    订éĺħä¸ĵæłı
    -0.08
     paran
    -0.08
    åľ¨å¿ħ
    -0.07
    ä¸Ģæī«
    -0.07
    acular
    -0.07
     parenthesis
    -0.07
     seber
    -0.07
    è¯Ħä»·
    -0.07
    éĽĨç»ĵåı·
    -0.07
    hai
    -0.07
    POSITIVE LOGITS
    为äºĨæĸ¹ä¾¿
    0.10
    æĸ¹ä¾¿çļĦ
    0.09
    æĸ¹ä¾¿
    0.09
    -setup
    0.08
    为æĸ¹ä¾¿
    0.08
    æĽ´æĸ¹ä¾¿
    0.08
     convenient
    0.08
    çİ°å®ŀ
    0.07
     convenience
    0.07
    real
    0.07
    Activations Density 0.014%

    No Known Activations