© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43093
    Prev
    Next
    INDEX
    Explanations

    media titles and names

    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
    nde
    -0.07
     Agen
    -0.07
     Lew
    -0.07
    æĹłèģĬ
    -0.07
    ä¸įæĪIJ
    -0.07
    æīŃ
    -0.07
     tyl
    -0.06
    ilst
    -0.06
    izz
    -0.06
     trash
    -0.06
    POSITIVE LOGITS
    åĭ¤åѦ
    0.07
    管çIJĨæĿ¡ä¾ĭ
    0.07
    ajar
    0.07
    åIJĪ
    0.07
     (*((
    0.07
    æ¸ł
    0.07
    dar
    0.07
    循åºı
    0.06
    :disable
    0.06
    ��
    0.06
    Activations Density 0.005%

    No Known Activations