© 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. 59773
    Prev
    Next
    INDEX
    Explanations

    C/C++ code constructs

    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
    ÙĦاس
    -0.08
    æīĺ
    -0.07
    برا
    -0.07
    åĴĶåļĵ
    -0.07
    itest
    -0.06
    gett
    -0.06
    EDIT
    -0.06
     Nog
    -0.06
     Lou
    -0.06
    å°±çľĭ
    -0.06
    POSITIVE LOGITS
    åıĪåı«
    0.11
    åıĪ称为
    0.11
     ÙĩÙħاÙĨ
    0.11
    ä¿Ĺ称
    0.11
    åħ¶å®ŀå°±æĺ¯
    0.11
    åį³ä¸º
    0.10
    ä¹Łåı«
    0.10
    åıĪåIJį
    0.10
    ä¹Łç§°ä¸º
    0.09
    åĪ«åIJį
    0.09
    Activations Density 0.097%

    No Known Activations