© 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. 44237
    Prev
    Next
    INDEX
    Explanations

    unnecessary allocation or copying

    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
    acman
    -0.09
    eaux
    -0.08
    -validator
    -0.08
    顾åIJįæĢĿä¹ī
    -0.08
    maxcdn
    -0.08
     =========================================================================
    -0.08
    ç¼Ń
    -0.08
    à¸Ńาร
    -0.08
    åŃĿ
    -0.08
    ä¸Ģç»ıåıijçİ°
    -0.08
    POSITIVE LOGITS
    ä¸įå¿ħè¦ģçļĦ
    0.10
     unnecessarily
    0.10
     unnecessary
    0.09
     desn
    0.09
    æ¯ı次éĥ½
    0.09
    æ¯ıä¸Ģ次
    0.09
     repeatedly
    0.08
    两次
    0.08
    æ¯ı次
    0.08
    å¤ļ次
    0.08
    Activations Density 0.092%

    No Known Activations