© 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. 29598
    Prev
    Next
    INDEX
    Explanations

    intellectual physicists and technical discussions

    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
    incontro
    -0.10
     Legislat
    -0.10
    ahre
    -0.10
    家天ä¸ĭ
    -0.09
    æĸ°éĹ»ç½ij
    -0.09
    naver
    -0.09
    ç»ıçIJĨæĭĽèģĺ
    -0.09
    æĸĩåѦç½ij
    -0.09
    ãĥ¼ãĤ¸ãĤ§
    -0.09
    éĺħè¯»æľ¬æĸĩåīį
    -0.09
    POSITIVE LOGITS
     intellectual
    0.07
     Technical
    0.06
     physicist
    0.06
     "
    0.06
     physicists
    0.06
     Intellectual
    0.06
    è¿Ľåº¦
    0.06
    审éĺħ
    0.06
     technical
    0.06
     interdisciplinary
    0.06
    Activations Density 1.116%

    No Known Activations